Tarik Moussa
|
b803811701
|
feat(mcp): FastMCP server exposing read-only KB tools (stdio)
Implements F-14: thin FastMCP wrapper over existing codex domain modules.
Seven read-only tools: search, ask, wiki_read, wiki_list, discover_leads,
provenance_verify, synthesis_browse. All optional-feature tools degrade
gracefully to {"error": "feature not available"} instead of crashing.
Adds mcp[cli]>=1.0 dependency and codex-mcp console_script entry-point.
28 new tests across test_server, test_search, test_readonly, test_graceful,
test_http_auth — all green; 0 regressions in existing 172 tests.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-06-14 08:55:49 +02:00 |
|
Tarik Moussa
|
1df9be6563
|
feat(F-09): rich parsing — formula + figure extraction
- codex/parsing/mathpix.py: pix2tex (local, CPU) primary + MathPix API
optional; bbox heuristic h>15px, math-char-count>5; singleton model cache
- codex/parsing/figures.py: pymupdf embedded-image extraction → PNG;
caption detection via proximity + "Figure/Fig./Abbildung" prefix
- codex/models.py: FormulaChunk + FigureChunk dataclasses (R-10/R-11)
- codex/ingest.py: --rich flag wires formula+figure extraction post-ingest
- codex/cli.py: search_app sub-typer (paper + formula subcommands),
--rich flag on ingest; wiki_app from F-12 preserved intact
- codex/config.py: mathpix_app_id/key, pix2tex_fallback, figures_dir
- infra/schema.sql: formulas + figures tables with HNSW pgvector indexes
- pyproject.toml: pymupdf>=1.24, pix2tex>=0.1.4
- tests/parsing/test_mathpix.py + test_figures.py: 31 tests (mock pix2tex
+ MathPix HTTP, real pymupdf on synthetic PDF)
Gate: 158 passed, ruff clean, mypy clean (20 files)
Requirements: R-10 R-11 R-12 R-13 R-14 → done
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-06-14 01:16:24 +02:00 |
|
Tarik Moussa
|
8eca4ebe12
|
fix(deps): add flagembedding>=1.2 for BGE-M3 hybrid encode (ADR-0002)
SentenceTransformer.encode() lacks return_dense/return_sparse kwargs;
BGEM3FlagModel provides the correct hybrid API.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-06-04 23:42:04 +02:00 |
|
Tarik Moussa
|
e7ac7766a5
|
feat: initial project scaffold
pyproject.toml (Python 3.12, uv), codex/ package (config, db, models),
infra/ (docker-compose + schema), .env.example, .gitignore, README.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
|
2026-06-04 11:19:10 +02:00 |
|