contexara 0.1.0__tar.gz

contexara-0.1.0/.gitignore

@@ -0,0 +1,351 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[codz]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py.cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+.pybuilder/
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# UV
+#   Similar to Pipfile.lock, it is generally recommended to include uv.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#uv.lock
+
+# poetry
+#   Similar to Pipfile.lock, it is generally recommended to include poetry.lock in version control.
+#   This is especially recommended for binary packages to ensure reproducibility, and is more
+#   commonly ignored for libraries.
+#   https://python-poetry.org/docs/basic-usage/#commit-your-poetrylock-file-to-version-control
+#poetry.lock
+#poetry.toml
+
+# pdm
+#   Similar to Pipfile.lock, it is generally recommended to include pdm.lock in version control.
+#   pdm recommends including project-wide configuration in pdm.toml, but excluding .pdm-python.
+#   https://pdm-project.org/en/latest/usage/project/#working-with-version-control
+#pdm.lock
+#pdm.toml
+.pdm-python
+.pdm-build/
+
+# pixi
+#   Similar to Pipfile.lock, it is generally recommended to include pixi.lock in version control.
+#pixi.lock
+#   Pixi creates a virtual environment in the .pixi directory, just like venv module creates one
+#   in the .venv directory. It is recommended not to include this directory in version control.
+.pixi
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow and github.com/pdm-project/pdm
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.envrc
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
+
+# Cython debug symbols
+cython_debug/
+
+# PyCharm
+#  JetBrains specific template is maintained in a separate JetBrains.gitignore that can
+#  be found at https://github.com/github/gitignore/blob/main/Global/JetBrains.gitignore
+#  and can be added to the global gitignore or merged into this file.  For a more nuclear
+#  option (not recommended) you can uncomment the following to ignore the entire idea folder.
+#.idea/
+
+# Abstra
+# Abstra is an AI-powered process automation framework.
+# Ignore directories containing user credentials, local state, and settings.
+# Learn more at https://abstra.io/docs
+.abstra/
+
+# Visual Studio Code
+#  Visual Studio Code specific template is maintained in a separate VisualStudioCode.gitignore 
+#  that can be found at https://github.com/github/gitignore/blob/main/Global/VisualStudioCode.gitignore
+#  and can be added to the global gitignore or merged into this file. However, if you prefer, 
+#  you could uncomment the following to ignore the entire vscode folder
+# .vscode/
+
+# Ruff stuff:
+.ruff_cache/
+
+# PyPI configuration file
+.pypirc
+
+# Cursor
+#  Cursor is an AI-powered code editor. `.cursorignore` specifies files/directories to
+#  exclude from AI features like autocomplete and code analysis. Recommended for sensitive data
+#  refer to https://docs.cursor.com/context/ignore-files
+.cursorignore
+.cursorindexingignore
+
+# Marimo
+marimo/_static/
+marimo/_lsp/
+__marimo__/
+
+
+# Platform (Next.js)
+platform/web/node_modules/
+platform/web/.next/
+platform/web/.build-performance/
+platform/web/.env.local
+platform/web/tsconfig.tsbuildinfo
+!platform/web/lib/
+
+# Clients (installer)
+clients/installer/node_modules/
+
+# Platform (Capture Engine local dev artifacts)
+platform/api/.venv/
+platform/api/.local_storage/
+
+# Engines (processing) — generated ONNX exports and caches, never source
+engines/processing/_onnx_*/
+# ~2.3GB BGE-M3 ONNX weights, downloaded via infra/DEPLOY.md step 5 (hf download), not committed
+engines/processing/onnx-bge-m3/
+engines/processing/.venv/
+engines/processing/__pycache__/
+engines/processing/experiments/__pycache__/
+
+# Clients (hooks) — compiled Go binary, regenerable via `go build`, not source
+clients/hooks/claude-code-hook.exe
+
+# Build temp
+.build-tmp/
+
+# Temp files for testing / Misc
+bedrock_llm.py
+database/
+my-tests/
+/docs/
+tests/.tmp/
+tests/.pytest_tmp/
+# Local experiments (not tracked)
+dev/
+frontend/node_modules/
+# REAL BUG FIXED 2026-09-21: this was a bare "memory/" (no leading
+# slash), which matches ANY directory named "memory" anywhere in the
+# repo, not just a root-level one. It silently swallowed the real,
+# committed feature directories platform/web/components/memory/ and
+# platform/web/app/(dashboard)/memory/ for their entire lifetime --
+# never once in git history until this fix, discovered only when a
+# Vercel build failed on a genuinely real, on-disk import
+# (MemoryInspector.tsx -> ../memory/SourceDetails) that git had never
+# tracked. Scoped to the repo root explicitly so it can never again
+# collide with a legitimately-named nested directory.
+/memory/
+benchmarks/longmemeval/longmemeval_oracle.json 
+"benchmarks/longmemeval/longmemeval_oracle/eval_results.txt" 
+"benchmarks/longmemeval/longmemveal_s/longmemeval_s_cleaned.json" 
+"benchmarks/longmemeval/longmemeval_oracle/eval_results.txt" 
+"benchmarks/longmemeval/longmemveal_s/longmemeval_s_cleaned.json" 
+benchmarks/longmemeval/longmemeval_s/*.json
+
+Josefin_Sans
+
+# BEAM benchmark dataset (5.4MB parquet) — data, not code
+benchmarks/**/*.parquet
+
+# Claude Code local tool-permission config — machine-specific, not project content
+.claude/
+# Local retrieval scratch files (kept on disk, never committed)
+engines/retrieval/inspect_user_turns.py
+engines/retrieval/response.json
+
+# ─── Benchmark and eval OUTPUT (2026-09-01) ───
+# Regenerable artifacts from LoCoMo/BEAM runs: predictions, scores, judged
+# output, per-conversation cost logs, evidence maps. Added because 56
+# untracked paths had accumulated on the VM, and a noisy `git status` is how
+# a genuinely stranded file goes unnoticed (see infra/scripts/check_git_sync.sh
+# and the Qdrant ulimits commit that nearly died in that noise).
+#
+# Deliberately NOT ignoring the harnesses, scorers or committed baselines
+# (e.g. research/hardning-ctx/m8_baseline_frozen.json) — those are the record
+# of what was measured and must stay in git.
+benchmarks/**/m8_results/
+benchmarks/**/m9_results/
+benchmarks/**/m8_beam_results/
+benchmarks/**/m9_beam_results/
+benchmarks/**/m9_beam1m_results/
+benchmarks/**/predictions*.json
+benchmarks/**/*_cost_result.txt
+benchmarks/**/*_probe_results.json
+benchmarks/**/locomo_window_map.json
+engines/processing/*_evidence_map.json
+full_conv41_results.txt
+
+# Hand-edited backups of tracked config. These are a smell rather than an
+# artifact: production config belongs in git, not in a .bak beside it.
+*.bak
+
+# Large benchmark/experiment artifacts that exceed GitHub's 100MB file
+# limit (real push rejections hit 2026-09-10 for all three) -- these are
+# generated/downloaded data, not source, and belong on the machine that
+# produced them, not in git history.
+benchmarks/longmemeval_s/longmemeval_s_cleaned.json
+codex-reserach/results/full/beam/beam.sqlite3
+codex-reserach/results/full/locomo/locomo.sqlite3
+
+# UNTRIAGED EXPERIMENTAL WORK (2026-09-21) -- gitignored for git-status
+# hygiene ONLY, not a verdict on the work itself. Reviewed via two
+# dedicated agent passes before this list was written: nothing here was
+# found to be disposable scratch -- the V1 retrieval/consolidation
+# rebuild (engines/retrieval/v1/, engines/processing/consolidation/) is
+# real, substantial, tested alternative-architecture work with its own
+# bug-fix history; its frozen baseline (61.2-61.8% LoCoMo judge accuracy,
+# n=152) sits below both its own 80% launch gate and today's measured
+# production number (67.7%, n=1540), but the two were never benchmarked
+# head-to-head at matched scale -- that comparison is genuinely
+# unfinished, not settled. Nothing here should be deleted or assumed
+# dead; this entry exists so it stops cluttering `git status` while its
+# real fate (commit as an alternative-architecture reference, revive,
+# or formally retire) gets decided in a dedicated future pass.
+engines/processing/consolidation/
+engines/retrieval/v1/
+benchmarks/v1_eval/
+production_docs/
+research/
+z-bench/
+z-loop-agentic/
+z-multimodal-ctx/
+z-ui-ux/
+engines/processing/deepseek_extractor.py
+engines/processing/ctx_index.py
+engines/processing/test_stage3.py
+engines/processing/test_stage3_scale.py
+engines/processing/test_stage4.py
+engines/processing/test_stage4_perf.py
+engines/processing/test_conv44_comparison.py
+engines/processing/test_bitemporal_repair.py
+benchmarks/beam100k/build_judge_detail.py
+benchmarks/beam100k/mem0_beam_answer.py
+benchmarks/beam100k/mem0_nugget_judge.py
+benchmarks/beam100k/run_judge_eval.py
+benchmarks/locomo/deep_recall_force_test.py
+benchmarks/longmemeval_s/backfill_qdrant_sync.py
+benchmarks/longmemeval_s/diag_multisession_rank.py
+benchmarks/longmemeval_s/m9_production_accuracy_eval_longmemeval.py
+scripts/test_gemma_context_builder.py

contexara-0.1.0/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2026 Contexara
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.