v2.1.0

[2.1.0] - 2026-04-05

Code files now chunk at function and class boundaries via tree-sitter,
clickable editor links land you at the right line from search results,
and per-collection model configuration means you can point different
collections at different embedding models. 25+ community PRs fix
embedding stability, BM25 accuracy, and cross-platform launcher issues.

Changes

• AST-aware chunking for code files via web-tree-sitter. Supported
  languages: TypeScript/JavaScript, Python, Go, and Rust. Code files
  are chunked at function, class, and import boundaries instead of
  arbitrary text positions. Markdown and unknown file types are unchanged.
  --chunk-strategy <auto|regex> flag on qmd embed and qmd query
  (default regex). SDK: chunkStrategy option on embed() and
  search(). qmd status shows grammar availability.
• qmd bench <fixture.json> command for search quality benchmarks.
  Measures precision@k, recall, MRR, and F1 across BM25, vector, hybrid,
  and full pipeline backends. Ships with an example fixture against
  the eval-docs test collection. #470 (thanks @jmilinovich)
• models: section in index.yml lets you configure embed, rerank,
  and generate model URIs per collection. Resolution order is
  config > env var (QMD_EMBED_MODEL, QMD_RERANK_MODEL,
  QMD_GENERATE_MODEL) > built-in default. #502
  (thanks @JohnRichardEnders)
• CLI search output now emits clickable OSC 8 terminal hyperlinks when
  stdout is a TTY. Links resolve qmd:// paths to absolute filesystem
  paths and open in editors via URI templates (default:
  vscode://file/{path}:{line}:{col}). Configure with QMD_EDITOR_URI
  or editor_uri in the YAML config. #508 (thanks @danmackinlay)
• --no-rerank flag skips the reranking step in qmd query — useful
  when you want fast results or don't have a GPU. Also exposed as
  rerank: false on the MCP query tool. #370 (thanks @mvanhorn),
  #478 (thanks @zestyboy)
• ONNX conversion script for deploying embedding models via
  Transformers.js. #399 (thanks @shreyaskarnik)
• GitHub Actions workflow to build the Nix flake on Linux and macOS.

Fixes

• Embedding: prevent qmd embed from running indefinitely when the
  embedding loop stalls. #458 (thanks @ccc-fff)
• Embedding: truncate oversized text before embedding to prevent GGML
  crash, and bound memory usage during batch embedding. #393
  (thanks @lskun), #395 (thanks @ProgramCaiCai)
• Embedding: set explicit embed context size (default 2048, configurable
  via QMD_EMBED_CONTEXT_SIZE) instead of using the model's full
  window. #500
• Embedding: error on dimension mismatch instead of silently rebuilding
  the vec0 table. #501
• Embedding: handle vec0 OR REPLACE limitation in insertEmbedding.
  #456 (thanks @antonio-mello-ai)
• Embedding: fix model selection when multiple models are configured.
  #494
• BM25: correct field weights to include all 3 FTS columns — title,
  body, and path were not weighted correctly. #462 (thanks @goldsr09)
• BM25: handle hyphenated tokens in FTS5 lex queries so terms like
  "real-time" match correctly. #463 (thanks @goldsr09)
• BM25: preserve underscores in search terms instead of stripping them.
  #404
• BM25: use CTE in searchFTS to prevent query planner regression with
  collection filter.
• Reranker: increase default context size 2048→4096 and make
  configurable via QMD_RERANK_CONTEXT_SIZE. Fix template overhead
  underestimate 200→512. #453 (thanks @builderjarvis)
• GPU: catch initialization failures and fall back to CPU instead of
  crashing.
• MCP: read version from package.json instead of hardcoding. #431
• MCP: include collection name in status output. #416
• Multi-get: support brace expansion patterns in glob matching. #424
• Launcher: prioritize package-lock.json to prevent Bun false
  positive. #385 (thanks @rymalia)
• Launcher: remove $BUN_INSTALL check that caused false Bun detection.
  #362 (thanks @syedair)
• Launcher: skip Git Bash path detection on WSL. #371
  (thanks @oysteinkrog)
• Model cache: respect XDG_CACHE_HOME for model cache directory. #457
  (thanks @antonio-mello-ai)
• SQLite: add macOS Homebrew SQLite support for Bun and restore
  actionable errors. #377 (thanks @serhii12)
• Pin zod to exact 4.2.1 to fix tsc build failure. #382
  (thanks @rymalia)
• Preserve dots and original case in handelize() — filenames like
  MEMORY.md no longer become memory-md. #475 (thanks @alexei-led)
• Include line in --json search output so editor integrations can
  jump directly to file:line. #506 (thanks @danmackinlay)
• Nix: fix paths in flake and make Bun dependency a fixed-output
  derivation so sandboxed Linux builds work offline. #479
  (thanks @surma-dump)
• Sync stale bun.lock (better-sqlite3 11.x → 12.x). CI and release
  script now use --frozen-lockfile to prevent recurrence. #386
  (thanks @Mic92)
• Approve native build scripts in pnpm so better-sqlite3 and
  tree-sitter modules compile correctly. Update vitest ^3.0.0 → ^3.2.4.

v2.0.1

[2.0.1] - 2026-03-10

Changes

• qmd skill install copies the packaged QMD skill into
  ~/.claude/commands/ for one-command setup. #355 (thanks @nibzard)

Fixes

• Fix Qwen3-Embedding GGUF filename case — HuggingFace filenames are
  case-sensitive, the lowercase variant returned 404. #349 (thanks @byheaven)
• Resolve symlinked global launcher path so qmd works correctly when
  installed via npm i -g. #352 (thanks @nibzard)

[2.0.0] - 2026-03-10

QMD 2.0 declares a stable library API. The SDK is now the primary interface —
the MCP server is a clean consumer of it, and the source is organized into
src/cli/ and src/mcp/. Also: Node 25 support and a runtime-aware bin wrapper
for bun installs.

Changes

• Stable SDK API with QMDStore interface — search, retrieval, collection/context
  management, indexing, lifecycle
• Unified search(): pass query for auto-expansion or queries for
  pre-expanded lex/vec/hyde — replaces the old query/search/structuredSearch split
• New getDocumentBody(), getDefaultCollectionNames(), Maintenance class
• MCP server rewritten as a clean SDK consumer — zero internal store access
• CLI and MCP organized into src/cli/ and src/mcp/ subdirectories
• Runtime-aware bin/qmd wrapper detects bun vs node to avoid ABI mismatches.
  Closes #319
• better-sqlite3 bumped to ^12.4.5 for Node 25 support. Closes #257
• Utility exports: extractSnippet, addLineNumbers, DEFAULT_MULTI_GET_MAX_BYTES

Fixes

• Remove unused import { resolve } in store.ts that shadowed local export

v2.0.0

[2.0.0] - 2026-03-10

QMD 2.0 declares a stable library API. The SDK is now the primary interface —
the MCP server is a clean consumer of it, and the source is organized into
src/cli/ and src/mcp/. Also: Node 25 support and a runtime-aware bin wrapper
for bun installs.

Changes

• Stable SDK API with QMDStore interface — search, retrieval, collection/context
  management, indexing, lifecycle
• Unified search(): pass query for auto-expansion or queries for
  pre-expanded lex/vec/hyde — replaces the old query/search/structuredSearch split
• New getDocumentBody(), getDefaultCollectionNames(), Maintenance class
• MCP server rewritten as a clean SDK consumer — zero internal store access
• CLI and MCP organized into src/cli/ and src/mcp/ subdirectories
• Runtime-aware bin/qmd wrapper detects bun vs node to avoid ABI mismatches.
  Closes #319
• better-sqlite3 bumped to ^12.4.5 for Node 25 support. Closes #257
• Utility exports: extractSnippet, addLineNumbers, DEFAULT_MULTI_GET_MAX_BYTES

Fixes

• Remove unused import { resolve } in store.ts that shadowed local export

v1.1.6

[1.1.6] - 2026-03-09

QMD can now be used as a library. import { createStore } from '@tobilu/qmd'
gives you the full search and indexing API — hybrid query, BM25, structured
search, collection/context management — without shelling out to the CLI.

Changes

• SDK / library mode: createStore({ dbPath, config }) returns a
  QMDStore with query(), search(), structuredSearch(), get(),
  multiGet(), and collection/context management methods. Supports inline
  config (no files needed) or a YAML config path.
• Package exports: package.json now declares main, types, and
  exports so bundlers and TypeScript resolve @tobilu/qmd correctly.

[1.1.5] - 2026-03-07

Ambiguous queries like "performance" now produce dramatically better results
when the caller knows what they mean. The new intent parameter steers all
five pipeline stages — expansion, strong-signal bypass, chunk selection,
reranking, and snippet extraction — without searching on its own. Design and
original implementation by Ilya Grigorik (@vyalamar) in #180.

Changes

• Intent parameter: optional intent string disambiguates queries across
  the entire search pipeline. Available via CLI (--intent flag or intent:
  line in query documents), MCP (intent field on the query tool), and
  programmatic API. Adapted from PR #180 (thanks @vyalamar).
• Query expansion: when intent is provided, the expansion LLM prompt
  includes Query intent: {intent}, matching the finetune training data
  format for better-aligned expansions.
• Reranking: intent is prepended to the rerank query so Qwen3-Reranker
  scores with domain context.
• Chunk selection: intent terms scored at 0.5× weight alongside query
  terms (1.0×) when selecting the best chunk per document for reranking.
• Snippet extraction: intent terms scored at 0.3× weight to nudge
  snippets toward intent-relevant lines without overriding query anchoring.
• Strong-signal bypass disabled with intent: when intent is provided, the
  BM25 strong-signal shortcut is skipped — the obvious keyword match may not
  be what the caller wants.
• MCP instructions: callers are now guided to provide intent on every
  search call for disambiguation.
• Query document syntax: intent: recognized as a line type. At most one
  per document, cannot appear alone. Grammar updated in docs/SYNTAX.md.

[1.1.2] - 2026-03-07

13 community PRs merged. GPU initialization replaced with node-llama-cpp's
built-in autoAttempt — deleting ~220 lines of manual fallback code and
fixing GPU issues reported across 10+ PRs in one shot. Reranking is faster
through chunk deduplication and a parallelism cap that prevents VRAM
exhaustion.

Changes

• GPU init: use node-llama-cpp's build: "autoAttempt" instead of manual
  GPU backend detection. Automatically tries Metal/CUDA/Vulkan and falls back
  gracefully. #310 (thanks @giladgd — the node-llama-cpp author)
• Query --explain: qmd query --explain exposes retrieval score traces
  — backend scores, per-list RRF contributions, top-rank bonus, reranker
  score, and final blended score. Works in JSON and CLI output. #242
  (thanks @vyalamar)
• Collection ignore patterns: ignore: ["Sessions/**", "*.tmp"] in
  collection config to exclude files from indexing. #304 (thanks @sebkouba)
• Multilingual embeddings: QMD_EMBED_MODEL env var lets you swap in
  models like Qwen3-Embedding for non-English collections. #273 (thanks
  @daocoding)
• Configurable expansion context: QMD_EXPAND_CONTEXT_SIZE env var
  (default 2048) — previously used the model's full 40960-token window,
  wasting VRAM. #313 (thanks @0xble)
• candidateLimit exposed: -C / --candidate-limit flag and MCP
  parameter to tune how many candidates reach the reranker. #255 (thanks
  @pandysp)
• MCP multi-session: HTTP transport now supports multiple concurrent
  client sessions, each with its own server instance. #286 (thanks @joelev)

Fixes

• Reranking performance: cap parallel rerank contexts at 4 to prevent
  VRAM exhaustion on high-core machines. Deduplicate identical chunk texts
  before reranking — same content from different files now shares a single
  reranker call. Cache scores by content hash instead of file path.
• Deactivate stale docs when all files are removed from a collection and
  qmd update is run. #312 (thanks @0xble)
• Handle emoji-only filenames (🐘.md → 1f418.md) instead of crashing.
  #308 (thanks @debugerman)
• Skip unreadable files during indexing (e.g. iCloud-evicted files returning
  EAGAIN) instead of crashing. #253 (thanks @jimmynail)
• Suppress progress bar escape sequences when stderr is not a TTY. #230
  (thanks @dgilperez)
• Emit format-appropriate empty output ([] for JSON, CSV header for CSV,
  etc.) instead of plain text "No results." #228 (thanks @amsminn)
• Correct Windows sqlite-vec package name (sqlite-vec-windows-x64) and add
  sqlite-vec-linux-arm64. #225 (thanks @ilepn)
• Fix claude plugin setup CLI commands in README. #311 (thanks @gi11es)

[1.1.1] - 2026-03-06

Fixes

• Reranker: truncate documents exceeding the 2048-token context window
  instead of silently producing garbage scores. Long chunks (e.g. from
  PDF ingestion) now get a fair ranking.
• Nix: add python3 and cctools to build dependencies. #214 (thanks
  @pcasaretto)

[1.1.0] - 2026-02-20

QMD now speaks in query documents — structured multi-line queries where every line is typed (lex:, vec:, hyde:), combining keyword precision with semantic recall. A single plain query still works exactly as before (it's treated as an implicit expand: and auto-expanded by the LLM). Lex now supports quoted phrases and negation ("C++ performance" -sports -athlete), making intent-aware disambiguation practical. The formal query grammar is documented in docs/SYNTAX.md.

The npm package now uses the standard #!/usr/bin/env node bin convention, replacing the custom bash wrapper. This fixes native module ABI mismatches when installed via bun and works on any platform with node >= 22 on PATH.

Changes

• Query document format: multi-line queries with typed sub-queries (lex:, vec:, hyde:). Plain queries remain the default (expand: implicit, but not written inside the document). First sub-query gets 2× fusion weight — put your strongest signal first. Formal grammar in docs/SYNTAX.md.
• Lex syntax: full BM25 operator support. "exact phrase" for verbatim matching; -term and -"phrase" for exclusions. Essential for disambiguation when a term is overloaded across domains (e.g. performance -sports -athlete).
• expand: shortcut: send a single plain query (or start the document with expand: on its only line) to auto-expand via the local LLM. Query documents themselves are limited to lex, vec, and hyde lines.
• MCP query tool (renamed from structured_search): rewrote the tool description to fully teach AI agents the query document format, lex syntax, and combination strategy. Includes worked examples with intent-aware lex.
• HTTP /query endpoint (renamed from /search; /search kept as silent alias).
• collections array filter: filter by multiple collections in a single query (collections: ["notes", "brain"]). Removed the single collection string param — array only.
• Collection include/exclude: includeByDefault: false hides a collection from all queries unless explicitly named via collections. CLI: qmd collection exclude <name> / qmd collection include <name>.
• Collection update-cmd: attach a shell command that runs before every qmd update (e.g. git stash && git pull --rebase --ff-only && git stash pop). CLI: qmd collection update-cmd <name> '<cmd>'.
• qmd status tips: shows actionable tips when collections lack context descriptions or update commands.
• qmd collection subcommands: show, update-cmd, include, exclude. Bare qmd collection now prints help.
• Packaging: replaced custom bash wrapper with standard #!/usr/bin/env node shebang on dist/qmd.js. Fixes native module ABI mismatches when installed via bun, and works on any platform where node >= 22 is on PATH.
• Removed MCP tools search, vector_search, deep_search — all superseded by query.
• Removed qmd context check command.
• CLI timing: each LLM step (expand, embed, rerank) prints elapsed time inline (Expanding query... (4.2s)).

Fixes

• qmd collection list shows [excluded] tag for collections with includeByDefault: false.
• Default searches now respect includeByDefault — excluded collections are skipped unless explicitly named.
• Fix main module detection when installed globally via npm/bun (symlink resolution).

v1.1.5

[1.1.5] - 2026-03-07

Ambiguous queries like "performance" now produce dramatically better results
when the caller knows what they mean. The new intent parameter steers all
five pipeline stages — expansion, strong-signal bypass, chunk selection,
reranking, and snippet extraction — without searching on its own. Design and
original implementation by Ilya Grigorik (@vyalamar) in #180.

Changes

• Intent parameter: optional intent string disambiguates queries across
  the entire search pipeline. Available via CLI (--intent flag or intent:
  line in query documents), MCP (intent field on the query tool), and
  programmatic API. Adapted from PR #180 (thanks @vyalamar).
• Query expansion: when intent is provided, the expansion LLM prompt
  includes Query intent: {intent}, matching the finetune training data
  format for better-aligned expansions.
• Reranking: intent is prepended to the rerank query so Qwen3-Reranker
  scores with domain context.
• Chunk selection: intent terms scored at 0.5× weight alongside query
  terms (1.0×) when selecting the best chunk per document for reranking.
• Snippet extraction: intent terms scored at 0.3× weight to nudge
  snippets toward intent-relevant lines without overriding query anchoring.
• Strong-signal bypass disabled with intent: when intent is provided, the
  BM25 strong-signal shortcut is skipped — the obvious keyword match may not
  be what the caller wants.
• MCP instructions: callers are now guided to provide intent on every
  search call for disambiguation.
• Query document syntax: intent: recognized as a line type. At most one
  per document, cannot appear alone. Grammar updated in docs/SYNTAX.md.

[1.1.2] - 2026-03-07

13 community PRs merged. GPU initialization replaced with node-llama-cpp's
built-in autoAttempt — deleting ~220 lines of manual fallback code and
fixing GPU issues reported across 10+ PRs in one shot. Reranking is faster
through chunk deduplication and a parallelism cap that prevents VRAM
exhaustion.

Changes

• GPU init: use node-llama-cpp's build: "autoAttempt" instead of manual
  GPU backend detection. Automatically tries Metal/CUDA/Vulkan and falls back
  gracefully. #310 (thanks @giladgd — the node-llama-cpp author)
• Query --explain: qmd query --explain exposes retrieval score traces
  — backend scores, per-list RRF contributions, top-rank bonus, reranker
  score, and final blended score. Works in JSON and CLI output. #242
  (thanks @vyalamar)
• Collection ignore patterns: ignore: ["Sessions/**", "*.tmp"] in
  collection config to exclude files from indexing. #304 (thanks @sebkouba)
• Multilingual embeddings: QMD_EMBED_MODEL env var lets you swap in
  models like Qwen3-Embedding for non-English collections. #273 (thanks
  @daocoding)
• Configurable expansion context: QMD_EXPAND_CONTEXT_SIZE env var
  (default 2048) — previously used the model's full 40960-token window,
  wasting VRAM. #313 (thanks @0xble)
• candidateLimit exposed: -C / --candidate-limit flag and MCP
  parameter to tune how many candidates reach the reranker. #255 (thanks
  @pandysp)
• MCP multi-session: HTTP transport now supports multiple concurrent
  client sessions, each with its own server instance. #286 (thanks @joelev)

Fixes

• Reranking performance: cap parallel rerank contexts at 4 to prevent
  VRAM exhaustion on high-core machines. Deduplicate identical chunk texts
  before reranking — same content from different files now shares a single
  reranker call. Cache scores by content hash instead of file path.
• Deactivate stale docs when all files are removed from a collection and
  qmd update is run. #312 (thanks @0xble)
• Handle emoji-only filenames (🐘.md → 1f418.md) instead of crashing.
  #308 (thanks @debugerman)
• Skip unreadable files during indexing (e.g. iCloud-evicted files returning
  EAGAIN) instead of crashing. #253 (thanks @jimmynail)
• Suppress progress bar escape sequences when stderr is not a TTY. #230
  (thanks @dgilperez)
• Emit format-appropriate empty output ([] for JSON, CSV header for CSV,
  etc.) instead of plain text "No results." #228 (thanks @amsminn)
• Correct Windows sqlite-vec package name (sqlite-vec-windows-x64) and add
  sqlite-vec-linux-arm64. #225 (thanks @ilepn)
• Fix claude plugin setup CLI commands in README. #311 (thanks @gi11es)

[1.1.1] - 2026-03-06

Fixes

• Reranker: truncate documents exceeding the 2048-token context window
  instead of silently producing garbage scores. Long chunks (e.g. from
  PDF ingestion) now get a fair ranking.
• Nix: add python3 and cctools to build dependencies. #214 (thanks
  @pcasaretto)

[1.1.0] - 2026-02-20

QMD now speaks in query documents — structured multi-line queries where every line is typed (lex:, vec:, hyde:), combining keyword precision with semantic recall. A single plain query still works exactly as before (it's treated as an implicit expand: and auto-expanded by the LLM). Lex now supports quoted phrases and negation ("C++ performance" -sports -athlete), making intent-aware disambiguation practical. The formal query grammar is documented in docs/SYNTAX.md.

The npm package now uses the standard #!/usr/bin/env node bin convention, replacing the custom bash wrapper. This fixes native module ABI mismatches when installed via bun and works on any platform with node >= 22 on PATH.

Changes

• Query document format: multi-line queries with typed sub-queries (lex:, vec:, hyde:). Plain queries remain the default (expand: implicit, but not written inside the document). First sub-query gets 2× fusion weight — put your strongest signal first. Formal grammar in docs/SYNTAX.md.
• Lex syntax: full BM25 operator support. "exact phrase" for verbatim matching; -term and -"phrase" for exclusions. Essential for disambiguation when a term is overloaded across domains (e.g. performance -sports -athlete).
• expand: shortcut: send a single plain query (or start the document with expand: on its only line) to auto-expand via the local LLM. Query documents themselves are limited to lex, vec, and hyde lines.
• MCP query tool (renamed from structured_search): rewrote the tool description to fully teach AI agents the query document format, lex syntax, and combination strategy. Includes worked examples with intent-aware lex.
• HTTP /query endpoint (renamed from /search; /search kept as silent alias).
• collections array filter: filter by multiple collections in a single query (collections: ["notes", "brain"]). Removed the single collection string param — array only.
• Collection include/exclude: includeByDefault: false hides a collection from all queries unless explicitly named via collections. CLI: qmd collection exclude <name> / qmd collection include <name>.
• Collection update-cmd: attach a shell command that runs before every qmd update (e.g. git stash && git pull --rebase --ff-only && git stash pop). CLI: qmd collection update-cmd <name> '<cmd>'.
• qmd status tips: shows actionable tips when collections lack context descriptions or update commands.
• qmd collection subcommands: show, update-cmd, include, exclude. Bare qmd collection now prints help.
• Packaging: replaced custom bash wrapper with standard #!/usr/bin/env node shebang on dist/qmd.js. Fixes native module ABI mismatches when installed via bun, and works on any platform where node >= 22 is on PATH.
• Removed MCP tools search, vector_search, deep_search — all superseded by query.
• Removed qmd context check command.
• CLI timing: each LLM step (expand, embed, rerank) prints elapsed time inline (Expanding query... (4.2s)).

Fixes

• qmd collection list shows [excluded] tag for collections with includeByDefault: false.
• Default searches now respect includeByDefault — excluded collections are skipped unless explicitly named.
• Fix main module detection when installed globally via npm/bun (symlink resolution).

v1.1.2

[1.1.2] - 2026-03-07

13 community PRs merged. GPU initialization replaced with node-llama-cpp's
built-in autoAttempt — deleting ~220 lines of manual fallback code and
fixing GPU issues reported across 10+ PRs in one shot. Reranking is faster
through chunk deduplication and a parallelism cap that prevents VRAM
exhaustion.

Changes

• GPU init: use node-llama-cpp's build: "autoAttempt" instead of manual
  GPU backend detection. Automatically tries Metal/CUDA/Vulkan and falls back
  gracefully. #310 (thanks @giladgd — the node-llama-cpp author)
• Query --explain: qmd query --explain exposes retrieval score traces
  — backend scores, per-list RRF contributions, top-rank bonus, reranker
  score, and final blended score. Works in JSON and CLI output. #242
  (thanks @vyalamar)
• Collection ignore patterns: ignore: ["Sessions/**", "*.tmp"] in
  collection config to exclude files from indexing. #304 (thanks @sebkouba)
• Multilingual embeddings: QMD_EMBED_MODEL env var lets you swap in
  models like Qwen3-Embedding for non-English collections. #273 (thanks
  @daocoding)
• Configurable expansion context: QMD_EXPAND_CONTEXT_SIZE env var
  (default 2048) — previously used the model's full 40960-token window,
  wasting VRAM. #313 (thanks @0xble)
• candidateLimit exposed: -C / --candidate-limit flag and MCP
  parameter to tune how many candidates reach the reranker. #255 (thanks
  @pandysp)
• MCP multi-session: HTTP transport now supports multiple concurrent
  client sessions, each with its own server instance. #286 (thanks @joelev)

Fixes

• Reranking performance: cap parallel rerank contexts at 4 to prevent
  VRAM exhaustion on high-core machines. Deduplicate identical chunk texts
  before reranking — same content from different files now shares a single
  reranker call. Cache scores by content hash instead of file path.
• Deactivate stale docs when all files are removed from a collection and
  qmd update is run. #312 (thanks @0xble)
• Handle emoji-only filenames (🐘.md → 1f418.md) instead of crashing.
  #308 (thanks @debugerman)
• Skip unreadable files during indexing (e.g. iCloud-evicted files returning
  EAGAIN) instead of crashing. #253 (thanks @jimmynail)
• Suppress progress bar escape sequences when stderr is not a TTY. #230
  (thanks @dgilperez)
• Emit format-appropriate empty output ([] for JSON, CSV header for CSV,
  etc.) instead of plain text "No results." #228 (thanks @amsminn)
• Correct Windows sqlite-vec package name (sqlite-vec-windows-x64) and add
  sqlite-vec-linux-arm64. #225 (thanks @ilepn)
• Fix claude plugin setup CLI commands in README. #311 (thanks @gi11es)

[1.1.1] - 2026-03-06

Fixes

• Reranker: truncate documents exceeding the 2048-token context window
  instead of silently producing garbage scores. Long chunks (e.g. from
  PDF ingestion) now get a fair ranking.
• Nix: add python3 and cctools to build dependencies. #214 (thanks
  @pcasaretto)

[1.1.0] - 2026-02-20

QMD now speaks in query documents — structured multi-line queries where every line is typed (lex:, vec:, hyde:), combining keyword precision with semantic recall. A single plain query still works exactly as before (it's treated as an implicit expand: and auto-expanded by the LLM). Lex now supports quoted phrases and negation ("C++ performance" -sports -athlete), making intent-aware disambiguation practical. The formal query grammar is documented in docs/SYNTAX.md.

The npm package now uses the standard #!/usr/bin/env node bin convention, replacing the custom bash wrapper. This fixes native module ABI mismatches when installed via bun and works on any platform with node >= 22 on PATH.

Changes

• Query document format: multi-line queries with typed sub-queries (lex:, vec:, hyde:). Plain queries remain the default (expand: implicit, but not written inside the document). First sub-query gets 2× fusion weight — put your strongest signal first. Formal grammar in docs/SYNTAX.md.
• Lex syntax: full BM25 operator support. "exact phrase" for verbatim matching; -term and -"phrase" for exclusions. Essential for disambiguation when a term is overloaded across domains (e.g. performance -sports -athlete).
• expand: shortcut: send a single plain query (or start the document with expand: on its only line) to auto-expand via the local LLM. Query documents themselves are limited to lex, vec, and hyde lines.
• MCP query tool (renamed from structured_search): rewrote the tool description to fully teach AI agents the query document format, lex syntax, and combination strategy. Includes worked examples with intent-aware lex.
• HTTP /query endpoint (renamed from /search; /search kept as silent alias).
• collections array filter: filter by multiple collections in a single query (collections: ["notes", "brain"]). Removed the single collection string param — array only.
• Collection include/exclude: includeByDefault: false hides a collection from all queries unless explicitly named via collections. CLI: qmd collection exclude <name> / qmd collection include <name>.
• Collection update-cmd: attach a shell command that runs before every qmd update (e.g. git stash && git pull --rebase --ff-only && git stash pop). CLI: qmd collection update-cmd <name> '<cmd>'.
• qmd status tips: shows actionable tips when collections lack context descriptions or update commands.
• qmd collection subcommands: show, update-cmd, include, exclude. Bare qmd collection now prints help.
• Packaging: replaced custom bash wrapper with standard #!/usr/bin/env node shebang on dist/qmd.js. Fixes native module ABI mismatches when installed via bun, and works on any platform where node >= 22 is on PATH.
• Removed MCP tools search, vector_search, deep_search — all superseded by query.
• Removed qmd context check command.
• CLI timing: each LLM step (expand, embed, rerank) prints elapsed time inline (Expanding query... (4.2s)).

Fixes

• qmd collection list shows [excluded] tag for collections with includeByDefault: false.
• Default searches now respect includeByDefault — excluded collections are skipped unless explicitly named.
• Fix main module detection when installed globally via npm/bun (symlink resolution).

v1.1.1

[1.1.1] - 2026-03-06

Fixes

• Reranker: truncate documents exceeding the 2048-token context window
  instead of silently producing garbage scores. Long chunks (e.g. from
  PDF ingestion) now get a fair ranking.
• Nix: add python3 and cctools to build dependencies. #214 (thanks
  @pcasaretto)

[1.1.0] - 2026-02-20

QMD now speaks in query documents — structured multi-line queries where every line is typed (lex:, vec:, hyde:), combining keyword precision with semantic recall. A single plain query still works exactly as before (it's treated as an implicit expand: and auto-expanded by the LLM). Lex now supports quoted phrases and negation ("C++ performance" -sports -athlete), making intent-aware disambiguation practical. The formal query grammar is documented in docs/SYNTAX.md.

The npm package now uses the standard #!/usr/bin/env node bin convention, replacing the custom bash wrapper. This fixes native module ABI mismatches when installed via bun and works on any platform with node >= 22 on PATH.

Changes

• Query document format: multi-line queries with typed sub-queries (lex:, vec:, hyde:). Plain queries remain the default (expand: implicit, but not written inside the document). First sub-query gets 2× fusion weight — put your strongest signal first. Formal grammar in [docs/SYNTAX.md](https://github.com/tobi/qmd/blob/main/docs/SYNTAX.md).
• Lex syntax: full BM25 operator support. "exact phrase" for verbatim matching; -term and -"phrase" for exclusions. Essential for disambiguation when a term is overloaded across domains (e.g. performance -sports -athlete).
• expand: shortcut: send a single plain query (or start the document with expand: on its only line) to auto-expand via the local LLM. Query documents themselves are limited to lex, vec, and hyde lines.
• MCP query tool (renamed from structured_search): rewrote the tool description to fully teach AI agents the query document format, lex syntax, and combination strategy. Includes worked examples with intent-aware lex.
• HTTP /query endpoint (renamed from /search; /search kept as silent alias).
• collections array filter: filter by multiple collections in a single query (collections: ["notes", "brain"]). Removed the single collection string param — array only.
• Collection include/exclude: includeByDefault: false hides a collection from all queries unless explicitly named via collections. CLI: qmd collection exclude <name> / qmd collection include <name>.
• Collection update-cmd: attach a shell command that runs before every qmd update (e.g. git stash && git pull --rebase --ff-only && git stash pop). CLI: qmd collection update-cmd <name> '<cmd>'.
• qmd status tips: shows actionable tips when collections lack context descriptions or update commands.
• qmd collection subcommands: show, update-cmd, include, exclude. Bare qmd collection now prints help.
• Packaging: replaced custom bash wrapper with standard #!/usr/bin/env node shebang on dist/qmd.js. Fixes native module ABI mismatches when installed via bun, and works on any platform where node >= 22 is on PATH.
• Removed MCP tools search, vector_search, deep_search — all superseded by query.
• Removed qmd context check command.
• CLI timing: each LLM step (expand, embed, rerank) prints elapsed time inline (Expanding query... (4.2s)).

Fixes

• qmd collection list shows [excluded] tag for collections with includeByDefault: false.
• Default searches now respect includeByDefault — excluded collections are skipped unless explicitly named.
• Fix main module detection when installed globally via npm/bun (symlink resolution).

v1.0.7

[1.0.7] - 2026-02-18

Changes

• LLM: add LiquidAI LFM2-1.2B as an alternative base model for query
  expansion fine-tuning. LFM2's hybrid architecture (convolutions + attention)
  is 2x faster at decode/prefill vs standard transformers — good fit for
  on-device inference.
• CLI: support multiple -c flags to search across several collections at
  once (e.g. qmd search -c notes -c journals "query"). #191 (thanks
  @openclaw)

Fixes

• Return empty JSON array [] instead of no output when --json search
  finds no results.
• Resolve relative paths passed to --index so they don't produce malformed
  config entries.
• Respect XDG_CONFIG_HOME for collection config path instead of always
  using ~/.config. #190 (thanks @openclaw)
• CLI: empty-collection hint now shows the correct collection add command.
  #200 (thanks @vincentkoc)

[1.0.6] - 2026-02-16

Changes

• CLI: qmd status now shows models with full HuggingFace links instead of
  static names in --help. Model info is derived from the actual configured
  URIs so it stays accurate if models change.
• Release tooling: pre-push hook handles non-interactive shells (CI, editors)
  gracefully — warnings auto-proceed instead of hanging on a tty prompt.
  Annotated tags now resolve correctly for CI checks.

[1.0.5] - 2026-02-16

The npm package now ships compiled JavaScript instead of raw TypeScript,
removing the tsx runtime dependency. A new /release skill automates the
full release workflow with changelog validation and git hook enforcement.

Changes

• Build: compile TypeScript to dist/ via tsc so the npm package no longer
  requires tsx at runtime. The qmd shell wrapper now runs dist/qmd.js
  directly.
• Release tooling: new /release skill that manages the full release
  lifecycle — validates changelog, installs git hooks, previews release notes,
  and cuts the release. Auto-populates [Unreleased] from git history when
  empty.
• Release tooling: scripts/extract-changelog.sh extracts cumulative notes
  for the full minor series (e.g. 1.0.0 through 1.0.5) for GitHub releases.
  Includes [Unreleased] content in previews.
• Release tooling: scripts/release.sh renames [Unreleased] to a versioned
  heading and inserts a fresh empty [Unreleased] section automatically.
• Release tooling: pre-push git hook blocks v* tag pushes unless
  package.json version matches the tag, a changelog entry exists, and CI
  passed on GitHub.
• Publish workflow: GitHub Actions now builds TypeScript, creates a GitHub
  release with cumulative notes extracted from the changelog, and publishes
  to npm with provenance.

[1.0.0] - 2026-02-15

QMD now runs on both Node.js and Bun, with up to 2.7x faster reranking
through parallel GPU contexts. GPU auto-detection replaces the unreliable
gpu: "auto" with explicit CUDA/Metal/Vulkan probing.

Changes

• Runtime: support Node.js (>=22) alongside Bun via a cross-runtime SQLite
  abstraction layer (src/db.ts). bun:sqlite on Bun, better-sqlite3 on
  Node. The qmd wrapper auto-detects a suitable Node.js install via PATH,
  then falls back to mise, asdf, nvm, and Homebrew locations.
• Performance: parallel embedding & reranking via multiple LlamaContext
  instances — up to 2.7x faster on multi-core machines.
• Performance: flash attention for ~20% less VRAM per reranking context,
  enabling more parallel contexts on GPU.
• Performance: right-sized reranker context (40960 → 2048 tokens, 17x less
  memory) since chunks are capped at ~900 tokens.
• Performance: adaptive parallelism — context count computed from available
  VRAM (GPU) or CPU math cores rather than hardcoded.
• GPU: probe for CUDA, Metal, Vulkan explicitly at startup instead of
  relying on node-llama-cpp's gpu: "auto". qmd status shows device info.
• Tests: reorganized into flat test/ directory with vitest for Node.js and
  bun test for Bun. New eval-bm25 and store.helpers.unit suites.

Fixes

• Prevent VRAM waste from duplicate context creation during concurrent
  embedBatch calls — initialization lock now covers the full path.
• Collection-aware FTS filtering so scoped keyword search actually restricts
  results to the requested collection.

v1.0.6

[1.0.6] - 2026-02-16

Changes

• CLI: qmd status now shows models with full HuggingFace links instead of
  static names in --help. Model info is derived from the actual configured
  URIs so it stays accurate if models change.
• Release tooling: pre-push hook handles non-interactive shells (CI, editors)
  gracefully — warnings auto-proceed instead of hanging on a tty prompt.
  Annotated tags now resolve correctly for CI checks.

[1.0.5] - 2026-02-16

The npm package now ships compiled JavaScript instead of raw TypeScript,
removing the tsx runtime dependency. A new /release skill automates the
full release workflow with changelog validation and git hook enforcement.

Changes

• Build: compile TypeScript to dist/ via tsc so the npm package no longer
  requires tsx at runtime. The qmd shell wrapper now runs dist/qmd.js
  directly.
• Release tooling: new /release skill that manages the full release
  lifecycle — validates changelog, installs git hooks, previews release notes,
  and cuts the release. Auto-populates [Unreleased] from git history when
  empty.
• Release tooling: scripts/extract-changelog.sh extracts cumulative notes
  for the full minor series (e.g. 1.0.0 through 1.0.5) for GitHub releases.
  Includes [Unreleased] content in previews.
• Release tooling: scripts/release.sh renames [Unreleased] to a versioned
  heading and inserts a fresh empty [Unreleased] section automatically.
• Release tooling: pre-push git hook blocks v* tag pushes unless
  package.json version matches the tag, a changelog entry exists, and CI
  passed on GitHub.
• Publish workflow: GitHub Actions now builds TypeScript, creates a GitHub
  release with cumulative notes extracted from the changelog, and publishes
  to npm with provenance.

[1.0.0] - 2026-02-15

QMD now runs on both Node.js and Bun, with up to 2.7x faster reranking
through parallel GPU contexts. GPU auto-detection replaces the unreliable
gpu: "auto" with explicit CUDA/Metal/Vulkan probing.

Changes

• Runtime: support Node.js (>=22) alongside Bun via a cross-runtime SQLite
  abstraction layer (src/db.ts). bun:sqlite on Bun, better-sqlite3 on
  Node. The qmd wrapper auto-detects a suitable Node.js install via PATH,
  then falls back to mise, asdf, nvm, and Homebrew locations.
• Performance: parallel embedding & reranking via multiple LlamaContext
  instances — up to 2.7x faster on multi-core machines.
• Performance: flash attention for ~20% less VRAM per reranking context,
  enabling more parallel contexts on GPU.
• Performance: right-sized reranker context (40960 → 2048 tokens, 17x less
  memory) since chunks are capped at ~900 tokens.
• Performance: adaptive parallelism — context count computed from available
  VRAM (GPU) or CPU math cores rather than hardcoded.
• GPU: probe for CUDA, Metal, Vulkan explicitly at startup instead of
  relying on node-llama-cpp's gpu: "auto". qmd status shows device info.
• Tests: reorganized into flat test/ directory with vitest for Node.js and
  bun test for Bun. New eval-bm25 and store.helpers.unit suites.

Fixes

• Prevent VRAM waste from duplicate context creation during concurrent
  embedBatch calls — initialization lock now covers the full path.
• Collection-aware FTS filtering so scoped keyword search actually restricts
  results to the requested collection.

v1.0.5

[1.0.5] - 2026-02-16

The npm package now ships compiled JavaScript instead of raw TypeScript,
removing the tsx runtime dependency. A new /release skill automates the
full release workflow with changelog validation and git hook enforcement.

Changes

• Build: compile TypeScript to dist/ via tsc so the npm package no longer
  requires tsx at runtime. The qmd shell wrapper now runs dist/qmd.js
  directly.
• Release tooling: new /release skill that manages the full release
  lifecycle — validates changelog, installs git hooks, previews release notes,
  and cuts the release. Auto-populates [Unreleased] from git history when
  empty.
• Release tooling: scripts/extract-changelog.sh extracts cumulative notes
  for the full minor series (e.g. 1.0.0 through 1.0.5) for GitHub releases.
  Includes [Unreleased] content in previews.
• Release tooling: scripts/release.sh renames [Unreleased] to a versioned
  heading and inserts a fresh empty [Unreleased] section automatically.
• Release tooling: pre-push git hook blocks v* tag pushes unless
  package.json version matches the tag, a changelog entry exists, and CI
  passed on GitHub.
• Publish workflow: GitHub Actions now builds TypeScript, creates a GitHub
  release with cumulative notes extracted from the changelog, and publishes
  to npm with provenance.

[1.0.0] - 2026-02-15

QMD now runs on both Node.js and Bun, with up to 2.7x faster reranking
through parallel GPU contexts. GPU auto-detection replaces the unreliable
gpu: "auto" with explicit CUDA/Metal/Vulkan probing.

Changes

• Runtime: support Node.js (>=22) alongside Bun via a cross-runtime SQLite
  abstraction layer (src/db.ts). bun:sqlite on Bun, better-sqlite3 on
  Node. The qmd wrapper auto-detects a suitable Node.js install via PATH,
  then falls back to mise, asdf, nvm, and Homebrew locations.
• Performance: parallel embedding & reranking via multiple LlamaContext
  instances — up to 2.7x faster on multi-core machines.
• Performance: flash attention for ~20% less VRAM per reranking context,
  enabling more parallel contexts on GPU.
• Performance: right-sized reranker context (40960 → 2048 tokens, 17x less
  memory) since chunks are capped at ~900 tokens.
• Performance: adaptive parallelism — context count computed from available
  VRAM (GPU) or CPU math cores rather than hardcoded.
• GPU: probe for CUDA, Metal, Vulkan explicitly at startup instead of
  relying on node-llama-cpp's gpu: "auto". qmd status shows device info.
• Tests: reorganized into flat test/ directory with vitest for Node.js and
  bun test for Bun. New eval-bm25 and store.helpers.unit suites.

Fixes

• Prevent VRAM waste from duplicate context creation during concurrent
  embedBatch calls — initialization lock now covers the full path.
• Collection-aware FTS filtering so scoped keyword search actually restricts
  results to the requested collection.