- Add tsc build step (tsconfig.build.json) so npm package ships
compiled JS instead of raw TypeScript requiring tsx at runtime
- Update qmd wrapper and daemon spawn to use dist/qmd.js in
production while keeping tsx for development
- Add self-installing pre-push hook validating v* tag pushes:
package.json version match, changelog entry, CI status
- Add release.sh script that renames [Unreleased] to versioned
entry, bumps package.json, commits, and tags
- Add extract-changelog.sh for cumulative GitHub release notes
- Update publish workflow with build step and GitHub release creation
- Flesh out CHANGELOG.md with full history from 0.1.0 through 1.0.0
in Keep-a-Changelog format with PR/contributor attributions
- Add release standards and changelog guidelines to CLAUDE.md
Document both Node and Bun execution paths.
- Update install examples to `@tobilu/qmd` for npm and bun.
- Add npx/bunx one-off usage examples.
- Reflect Bun as first-class supported runtime in requirements.
Update README installation and quick-start commands to Node examples.
- replace bun install/link commands with npm-based Node workflow
- bump package version to 0.9.9 for CLI and MCP metadata
- keep Bun guidance as optional development/runtime note
Add Smart Chunking section explaining break point scoring, distance
decay formula, and code fence protection. Update token counts from
800 to 900 throughout.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Generated with PaperBanana (Gemini 3 Pro). Shows query expansion
fanning HyDE+Vec into vector searches, Lex into BM25, merged via
reciprocal rank fusion and LLM reranking.
* feat: MCP HTTP transport with daemon lifecycle
Add streaming HTTP transport as an alternative to stdio for the MCP
server. A long-lived HTTP server avoids reloading 3 GGUF models (~2GB)
on every client connection, reducing warm query latency from ~16s (CLI)
to ~10s.
New CLI surface:
qmd mcp --http [--port N] # foreground, default port 3000
qmd mcp --http --daemon # background, PID in ~/.cache/qmd/mcp.pid
qmd mcp stop # stop daemon via PID file
qmd status # now shows MCP daemon liveness
Server implementation (mcp.ts):
- Extract createMcpServer(store) shared by stdio and HTTP transports
- HTTP transport uses WebStandardStreamableHTTPServerTransport with
JSON responses (stateless, no SSE)
- /health endpoint with uptime, /mcp for MCP protocol, 404 otherwise
- Request logging to stderr with timestamps, tool names, query args
Daemon lifecycle (qmd.ts):
- PID file + log file management with stale PID detection
- Absolute paths in Bun.spawn (process.execPath + import.meta.path)
so daemon works regardless of cwd
- mkdirSync for cache dir on fresh installs
- Removes top-level SIGTERM/SIGINT handlers before starting HTTP
server so async cleanup in mcp.ts actually runs
Move hybridQuery() and vectorSearchQuery() into store.ts as standalone
functions that take a Store as first argument. Both CLI and MCP now
call the identical pipeline, eliminating the class of bugs where one
copy drifts from the other.
Shared pipeline (store.ts):
- hybridQuery(): BM25 probe → expand → FTS+vec search → RRF →
chunk → rerank (chunks only) → position-aware blending → dedup
- vectorSearchQuery(): expand → vec search → dedup → sort
- SearchHooks interface for optional progress callbacks
- Constants: STRONG_SIGNAL_MIN_SCORE, STRONG_SIGNAL_MIN_GAP,
RERANK_CANDIDATE_LIMIT (40), addLineNumbers()
Bugs fixed by unification:
- MCP now gets strong-signal short-circuit (was CLI-only)
- Reranker candidate limit unified at 40 (MCP had 30)
- File dedup added to hybrid query (MCP was missing it)
- Collection filter pushed into searchVec DB query
- Filter-then-slice ordering fixed (MCP was slice-then-filter)
* feat: type-routed query expansion — lex→FTS, vec/hyde→vector
expandQuery() now returns typed ExpandedQuery[] instead of string[],
preserving the lex/vec/hyde type info from the LLM's GBNF-structured
output. hybridQuery() and vectorSearchQuery() route searches by type:
lex queries go to FTS only, vec/hyde go to vector only.
Previously, every expanded query ran through BOTH backends — keyword
variants wasted embedding forward passes, semantic paraphrases wasted
BM25 lookups. Type routing eliminates ~4 calls/query with zero quality
loss (cross-backend noise actually hurt RRF fusion).
Cache format changed from newline-separated text to JSON (preserves
types). Old cache entries gracefully re-expand on first access.
CLI expansion tree now shows query types:
├─ original query
├─ lex: keyword variant
├─ vec: semantic meaning
└─ hyde: hypothetical document...
Benchmark (5 queries, 1756-doc index, warm LLM, Apple Silicon):
Metric Old (untyped) New (typed) Delta
Avg backend calls 10.0 6.0 -40%
Total wall time 1278ms 549ms -57%
Avg saved/query — — 146ms
"authentication setup" 12 → 7 calls 511 → 112ms
"database migration strategy" 10 → 6 calls 182 → 106ms
"how to handle errors in API" 10 → 6 calls 216 → 121ms
"meeting notes from last week" 10 → 6 calls 228 → 110ms
"performance optimization" 8 → 5 calls 141 → 100ms
Savings come from skipped embed() calls (~30-80ms each). FTS is
synchronous SQLite (~0ms), so lex→FTS routing is free while
vec/hyde→vector-only avoids wasted embedding passes.
* fix: MCP query snippets now use reranker's best chunk, not full body
extractSnippet() was scanning the entire document body for keyword
matches to build the snippet. But hybridQuery() already identified
the most relevant chunk via cross-attention reranking — rescanning
the full body is redundant and can land on a less relevant section
if the query terms appear elsewhere in the document.
CLI was already using bestChunk (set during the refactor). MCP was
still using body — a pre-existing inconsistency, not a regression.
* feat: dynamic MCP instructions + tool annotations
The MCP server now generates instructions at startup from actual index
state and injects them into the initialize response. LLMs see collection
names, document counts, content descriptions, and search strategy
guidance in their system prompt — zero tool calls needed for orientation.
Previously, the only guidance was generic static tool descriptions and
a user-invocable "query" prompt that no LLM would discover on its own.
An LLM connecting to QMD had no idea what collections existed, what they
contained, or how to scope searches effectively.
* change default port to 8181
* fix: BM25 score normalization was inverted
The normalization formula `1 / (1 + |bm25|)` is a decreasing function of
match strength. FTS5 BM25 scores are negative where more negative = better
match (e.g., -10 is strong, -0.5 is weak). The formula mapped:
strong match (raw -10) → 1/(1+10) = 9% ← should be highest
weak match (raw -0.5) → 1/(1+0.5) = 67% ← should be lowest
Three downstream effects:
1. `--min-score 0.5` (or MCP minScore: 0.5) filtered OUT strong matches
and kept only weak ones. The MCP instructions recommend this threshold.
2. CLI `formatScore()` color bands never showed green for BM25 results
(best matches scored ~9%, green threshold is 70%).
3. The strong signal optimization in hybridQuery (skip ~2s LLM expansion
when BM25 already has a clear winner) was dead code — strong matches
scored ~0.09, never reaching the 0.85 threshold.
Fix: `|x| / (1 + |x|)` — same (0,1) range, monotonic, no per-query
normalization needed, but now correctly maps strong → high, weak → low.
The normalization was born broken (Math.max(0, x) clamped all
negative BM25 to 0 → every score = 1.0), then PR #76 changed to
Math.abs which made scores vary but inverted the direction. Neither
state was ever correct.
* fix: rerank cache key ignores chunk content
The rerank cache key was (query, file, model) but the actual text sent
to the reranker is a keyword-selected chunk that varies by query terms.
Two different queries hitting the same file can select different chunks,
but the second query gets a stale cached score from the first chunk.
Example:
Query "auth flow" → selects chunk about authentication → score 0.92
Query "auth tokens" → same file, selects chunk about tokens
→ cache HIT on (query, file, model) → returns 0.92 from wrong chunk
Fix: include full chunk text in cache key. getCacheKey() already
SHA-256 hashes its inputs, so this adds no key bloat — just
disambiguation. Old cache entries become natural misses (different key
shape) and re-warm on next query.
* rename MCP tools for clarity, rewrite descriptions for LLM tool selection
Rename MCP tools: vsearch → vector_search, query → deep_search.
LLMs see these names — self-documenting names reduce reliance on
descriptions for tool selection. CLI commands stay unchanged
(qmd vsearch, qmd query) — different namespace, users type those.
Rewrite all search tool descriptions to be action-oriented:
- search: "Search by keyword. Finds documents containing exact
words and phrases in the query."
- vector_search: "Search by meaning. Finds relevant documents even
when they use different words than the query — handles synonyms,
paraphrases, and related concepts."
- deep_search: "Deep search. Auto-expands the query into variations,
searches each by keyword and meaning, and reranks for top hits
across all results."
Rewrite instructions ladder — each tool says what it does, no
"start here" / "escalate as needed" strategy language.
Delete the "query" prompt (registerPrompt) — it restated what
descriptions + instructions already cover. No LLM proactively
calls prompts/get to learn how to use tools.
* supress HTTP server logs during tests
- Add marketplace.json for Claude Code plugin installation
- Simplify skill status check to inline `qmd status` (portable across agents)
- Update SKILL.md MCP section, reference mcp-setup.md for manual config
- Clean up mcp-setup.md (remove redundant prerequisites)
- Rename MCP-SETUP.md to mcp-setup.md
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
* Add query expansion model finetuning infrastructure
- Training scripts for Qwen3-0.6B and 1.7B models
- Dataset generation from s-emanuilov/query-expansion
- Evaluation scripts comparing finetuned vs baseline models
- GRPO RL training script (optional improvement)
- Export script for GGUF conversion
Results:
- 0.6B finetuned: 95% format compliance (lex/vec/hyde)
- Baseline: 0% format compliance
- Dataset: 5,157 examples on HuggingFace Hub
Models available at:
- tobil/qmd-query-expansion-0.6B (recommended)
- tobil/qmd-query-expansion-train (dataset)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix GRPO training script for TRL API compatibility
- Use max_completion_length instead of max_new_tokens
- Use processing_class instead of tokenizer
- Use args instead of config for GRPOTrainer
- Add __name__ attribute to reward function class
- Accept **kwargs in reward function for extra TRL args
- Add new LoRA adapter after merging SFT weights
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Update README with final evaluation results
- 0.6B SFT: 95% format compliance (best)
- 0.6B GRPO: 0% (catastrophic forgetting from RL)
- 1.7B v2: training completed, evaluation pending
- Added GRPO evaluation results
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add comprehensive scoring system for query expansion
New scoring criteria (0-100 points):
- Format (30): Must have lex: and vec: prefixes
- Diversity (30): Multiple types, no echoing query, diverse expansions
- Hyde (20): Optional, concise, no newlines, no word repetition
- Quality (20): Lex=keywords, vec=natural language
See SCORING.md for full documentation.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add HuggingFace login and comprehensive scoring to GRPO v2 training
- Add explicit HF_TOKEN login before training
- Use SCORING.md criteria as RL reward function
- Conservative training: LR 1e-6, LoRA rank 4
- Reward scores: good=0.94, bad=0.38
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Refactor finetune folder: train/rl scripts with YAML configs
Major changes:
- train.py: Generic SFT training script using YAML config
- rl.py: Generic GRPO training script using YAML config
- configs/: YAML configs per training run (sft_v4.yaml, grpo_v4.yaml)
- dataset/: Data preparation scripts moved here
- tui.py: Interactive model testing interface
Training results:
- SFT v4: 98.8% avg score (all Excellent)
- GRPO v4: 0% (failed - model drifted to verbose explanations)
Removed per-model scripts (train_0.6B.py, train_1.7B.py, etc)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add named entity extraction to GRPO reward function
Key changes:
- Extract named entities (acronyms, proper nouns, technical terms)
- Heavy penalty (-30) when lex queries miss named entities
- Penalty (-15) for generic filler phrases like "find information about"
- Compound entity detection (TDS motorsports -> both words)
- Update GRPO config with KL regularization (beta=0.04)
- Lower learning rate (5e-7) and add max_steps (200)
Test results:
- "who is TDS motorsports" good: 1.00, bad: 0.30 (was 0.75)
- "how to use React hooks" good: 0.87, bad: 0.45 (was 0.75)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add chat template leakage detection to reward function
Zero reward for outputs containing:
- <|im_start|>, <|im_end|> tokens
- <think>, </think> tags (Qwen3 thinking mode)
- Role markers like \nassistant\n, \nuser\n
- <|endoftext|> token
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Strict format validation: every line must be lex:/vec:/hyde:
Any line that doesn't start with a valid prefix now returns 0.0
instead of just counting as a penalty. This prevents any prose,
explanations, bullet points, or other invalid content.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Clean up evaluation files
- Remove old versioned evaluation files (0.6B, 1.7B, baseline)
- Rename evaluation_v4.json -> evaluation_sft.json
- Rename evaluation_v4_grpo.json -> evaluation_grpo_failed.json
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Refactor evals into separate run and score scripts
New structure:
- evals/run.py: Generate model outputs to JSONL
- evals/score.py: Score outputs with detailed breakdown
- evals/queries.txt: Test queries (26 total)
Features:
- Supports both HF Hub and local model paths
- Named entity preservation scoring
- Chat template leakage detection
- Strict format validation (every line must be lex:/vec:/hyde:)
- Generic phrase detection
Usage:
uv run evals/run.py --model tobil/qmd-query-expansion-0.6B-v4
uv run evals/score.py evals/results_*.jsonl
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix GRPO model loading to use SFT base first
The GRPO adapter was trained on merged SFT weights, so loading it
directly on the base model results in 0% score. Added --sft-model
parameter to evals/run.py to load SFT first, then apply GRPO adapter.
With correct loading: GRPO scores 89.7% (all 26 queries Excellent).
Updated README with correct GRPO score and loading instructions.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix TUI to load GRPO models with SFT base first
GRPO adapters were trained on merged SFT weights, so they need SFT
loaded and merged first before applying the GRPO adapter.
Updated MODELS config to include sft_base path for GRPO models,
and load_model() now handles the SFT -> merge -> GRPO flow.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Update README for unified model repository structure
All models (0.6B, 1.7B, 4B) with SFT and GRPO variants now go into
a single HuggingFace repo (tobil/qmd-query-expansion) with subfolders
for each size and training method.
Updated loading examples to show subfolder-based model loading.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Update README with separate model repos
Changed from subfolder approach to separate repos per model since
trainer.push_to_hub() doesn't support subfolder argument.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Add 1.7B and 4B GRPO training and GGUF conversion scripts
Training scripts for GRPO fine-tuning:
- train_1.7B_grpo.py: GRPO training for Qwen3-1.7B
- train_4B_grpo.py: GRPO training for Qwen3-4B
GGUF conversion scripts:
- convert_1.7B_gguf.py: Merge SFT+GRPO adapters and convert to GGUF
- convert_4B_gguf.py: Merge SFT+GRPO adapters and convert to GGUF
All scripts use PEP 723 inline dependencies for HuggingFace Jobs.
Models published:
- tobil/qmd-query-expansion-1.7B-sft
- tobil/qmd-query-expansion-1.7B-grpo
- tobil/qmd-query-expansion-1.7B-gguf
- tobil/qmd-query-expansion-4B-sft
- tobil/qmd-query-expansion-4B-grpo
- tobil/qmd-query-expansion-4B-gguf
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Remove beads issue tracking
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Remove beads reference from CLAUDE.md
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix GRPO reward function to handle think blocks and end tokens
- Strip <|im_end|> token from completions (model output includes it)
- Change think_penalty to skipped_think bonus (+20 for not using think)
- Adjust max_possible to account for bonus (120/140)
- Fix typo in chat template artifact check
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Make TUI model list dynamic from HuggingFace Hub
- Fetch available qmd-query-expansion models from tobil/ on Hub
- Auto-detect model size (0.6B, 1.7B, 4B) and use correct base model
- Group models by type (SFT vs GRPO) in menu
- Skip GGUF repos in model listing
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Fix GRPO training: apply chat template to prompts
The SFT model was trained with chat template format but GRPO was
passing raw prompts. Now prompts are formatted with tokenizer.apply_chat_template()
so the model sees the same format it learned during SFT.
Also update extract_query_from_prompt to strip chat template artifacts.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
* Finetune 2.0: consolidate and simplify the entire training pipeline
Consolidate ~2,800 lines of duplicated code across 12 files into 5 clean,
well-documented files targeting Qwen3-1.7B end-to-end.
Key changes:
- Extract reward function into single source of truth (reward.py)
Previously duplicated 3x with divergent bugs across rl.py,
train_1.7B_grpo.py, and train_4B_grpo.py
- Unify training into one script with sft/grpo subcommands (train.py)
Replaces train.py + rl.py + train_1.7B_grpo.py + train_4B_grpo.py
- Merge eval generate+score into single eval.py
Replaces evals/run.py + evals/score.py
- Parameterize GGUF conversion by --size (convert_gguf.py)
Replaces convert_1.7B_gguf.py + convert_4B_gguf.py
- Fix critical bug: rl.py silently ignored beta/temperature from config,
causing the exact catastrophic drift its own comments warned about
- Fix prompt consistency: all files use /no_think chat template format
- Retarget configs from 0.6B to 1.7B
- Comprehensive README documenting the full pipeline
Removed: rl.py, train_1.7B_grpo.py, train_4B_grpo.py, convert_1.7B_gguf.py,
convert_4B_gguf.py, tui.py, evals/run.py, evals/score.py
Net: -3,429 lines, +382 lines
Co-Authored-By: Claude (claude-fudge-eap-cc) <noreply@anthropic.com>
* Add HF Jobs scripts, temporal query examples, and training results
- jobs/sft.py and jobs/grpo.py: self-contained scripts for
`hf jobs uv run` (no local GPU needed)
- 12 temporal/recency query examples in training data (e.g. "recent
news about Shopify" -> lex with years 2025/2026)
- 4 temporal test queries in evals/queries.txt
- README updated with HF Jobs workflow, training results, and
updated file structure
- Remove .beads tracking
SFT and GRPO successfully trained on A10G via HF Jobs:
SFT: eval loss 0.321, token accuracy 92.4%
GRPO: mean reward 0.757, 200 steps, KL 0.00048
Co-Authored-By: Claude (claude-fudge-eap-cc) <noreply@anthropic.com>
* Deploy fine-tuned GRPO model as default for query expansion
Switch from generic Qwen3-1.7B-Q8_0 (~2.2GB) to fine-tuned
qmd-query-expansion-1.7B-q4_k_m (~1.1GB). The fine-tuned Q4
scores 91.7% avg with 30/30 Excellent, outperforming the base Q8.
- Update default generate model in src/llm.ts
- Update README model table, architecture diagram, config block
- Add v2 training data, eval scripts, and quantize job
- Remove superseded v1 training data (5,742 → 1,000 examples)
- Update finetune README with v2 results and file structure
Co-Authored-By: Claude (claude-fudge-eap-cc) <noreply@anthropic.com>
---------
Co-authored-by: Claude Opus 4.5 <noreply@anthropic.com>
The code uses Qwen3-1.7B (~2.2GB) for query expansion, but the README
documented Qwen3-0.6B (~640MB) in three places:
- Model requirements table
- Architecture diagram
- Code configuration sample
This caused confusion when users saw a 2GB+ download instead of 640MB.
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Replace Ollama HTTP API with node-llama-cpp for local GGUF models
- Add structured query expansion using JSON schema grammar:
- Generates lexical query (for BM25), vector query, and HyDE
- Tree-style CLI output showing query types
- Fix vector search: use cosine distance instead of L2
- Format queries with embeddinggemma nomic-style prompts
- Rename ollama_cache table to llm_cache
- Add disposeDefaultLlamaCpp() for clean process exit
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add support for collection/path.md format in get command (checks if
first component is a known collection before treating as filesystem path)
- Add comprehensive output format tests verifying qmd:// URIs, docid,
and context in JSON, CSV, MD, XML, files, and CLI formats
- Add path normalization tests for various input formats:
qmd://, //, qmd:////, collection/path, and path:line suffix
- Add isolated test environments (createIsolatedTestEnv) to prevent
YAML config conflicts between test suites
- Add test fixture files test1.md and test2.md for path tests
- Update runQmd helper to accept custom configDir parameter
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Move all .ts files to src/ to clean up the project root:
- Created src/ directory and moved all TypeScript source and test files
- Updated qmd shell wrapper to point to src/qmd.ts
- Updated package.json scripts to use src/ paths
- Updated documentation (CLAUDE.md, README.md) to reflect new structure
- All imports remain relative within src/, no changes needed
- Tests pass with same results (192 pass, 75 fail - existing issues)
This improves project organization and makes the root directory cleaner.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
- Extract store.ts: database operations, search, document retrieval
- createStore() factory pattern for clean DB lifecycle management
- Unified DocumentResult type with optional body loading
- Snippet extraction with diff-style headers (@@ -line,count @@)
- Extract llm.ts: LLM abstraction layer with Ollama implementation
- Clean interface for embed, generate, rerank operations
- High-level rerankerLogprobsCheck with logprob-based scoring
- Query expansion support
- Extract formatter.ts: output formatting utilities
- Support for CLI, JSON, CSV, MD, XML formats
- MCP-specific CSV formatting
- Extract mcp.ts: MCP server using createStore() pattern
- Single DB connection for server lifetime (fixes closed DB errors)
- URL-decode resource paths for proper space/special char handling
- Add comprehensive test suites (215 tests total)
- store.test.ts: 96 tests covering all store operations
- llm.test.ts: 60 tests for LLM abstraction
- mcp.test.ts: 59 tests for MCP endpoints and resources
- All tests use mocked Ollama (errors on unmocked calls)
- Add bun run inspector script for MCP debugging
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add `qmd mcp` command to start stdio-based MCP server
- Expose tools: qmd_search, qmd_vsearch, qmd_query, qmd_get, qmd_status
- Add index health warnings for unembedded docs and stale indexes
- Return CSV format with text/csv mime type for search results
- Add MCP documentation and configuration examples to README
- Add @modelcontextprotocol/sdk and zod dependencies
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Add new tagline: on-device search engine for everything you need to remember
- Add Quick Start section with walkthrough of indexing multiple directories
- Add "Using with AI Agents" section showing --json and --files workflows
- Update output format example to reflect new CLI format with Title/Context/Score
- Document --all flag for returning all matches
- Fix architecture diagram: show BM25+Vector for all query variations
- Add position-aware blending percentages to diagram
- Update CLI commands: add → index, add-context, cleanup, status
- Document chunked embeddings (~6KB pieces with hash/seq/pos)
- Update schema section with new tables (path_contexts, ollama_cache)
- Rewrite How It Works flows with accurate pipeline details
- Fix output format examples to show ~/... paths
- Add --files and --json output options
🤖 Generated with [Claude Code](https://claude.com/claude-code)
