mapsmith 0.2.2__tar.gz → 0.4.0__tar.gz

mapsmith-0.4.0/.gitignore

@@ -0,0 +1,68 @@
+# Python
+__pycache__/
+*.py[cod]
+*.egg-info/
+dist/
+build/
+.venv/
+venv/
+.pytest_cache/
+.ruff_cache/
+
+# Data & outputs (never commit datasets)
+*.gpkg
+*.gpkg-journal
+*.shp
+*.shx
+*.dbf
+*.prj
+*.tif
+*.tiff
+*.parquet
+*.provenance.json
+data/
+# ...except the vendored spec artefacts: test dependencies, not datasets. This
+# has now bitten twice in the same way -- the validator was silently ignored
+# once, and on 2026-08-26 the schema next to it went the same way, because the
+# exception was a filename rather than a rule. Both times the conformance test
+# passed locally and CI could not find the file. The comment did not prevent the
+# second one, so `test_showcase.py` now checks that everything under
+# `tests/data/` is tracked: a rule that asserts a property without checking it
+# is worse than no rule.
+!tests/data/
+tests/data/*
+!tests/data/manifest_spec_validator.py
+!tests/data/manifest-v1.schema.json
+# The discovery benchmark: 95 queries written by a second model from work
+# scenarios, never from this catalog. It is tracked BECAUSE it is a dataset — an
+# evaluation set nobody can inspect is a claim, not a measurement.
+!tests/data/discovery_queries.json
+
+# Scratch databases: probing the DuckDB sandbox (ATTACH, COPY) drops these in
+# the repo root, and one of them reached a public commit before we noticed.
+*.db
+*.duckdb
+*.wal
+
+# OS / editors
+.DS_Store
+Thumbs.db
+.vscode/
+.idea/
+
+# Notebook gallery runtime data
+examples/data/
+
+# ...but the gallery's one real-world input is versioned on purpose: a
+# showcase built on synthetic terrain does not show what the tools do.
+!examples/fixtures/
+!examples/fixtures/*.tif
+uv.lock
+
+# The site is generated: `python site/build.py dist` rebuilds it from a real run.
+site/generated/
+
+# Written by `benchmarks/dashboard.py` and by MAPSMITH_DISCOVERY_LOG:
+# both hold the queries somebody typed, so they stay out of the repository.
+dashboard.html
+*.jsonl

mapsmith-0.4.0/.zenodo.json

@@ -0,0 +1,19 @@
+{
+  "upload_type": "software",
+  "title": "MapSmith: geospatial processing for AI agents, with verifiable provenance",
+  "version": "0.4.0",
+  "creators": [
+    {"name": "The MapSmith project"}
+  ],
+  "license": "agpl-3.0-or-later",
+  "access_right": "open",
+  "keywords": [
+    "GIS",
+    "geospatial",
+    "provenance",
+    "reproducibility",
+    "Model Context Protocol",
+    "MCP"
+  ],
+  "description": "<p>An MCP server that gives AI agents professional geoprocessing under a rule the agent cannot bend: every geometry and every number comes from a real engine run, never from the model.</p><p>Each operation that writes a dataset also writes a manifest beside it &mdash; the inputs and their hashes, the exact parameters, the coordinate-system decisions and the reason for each, the engine and its version, the environment that changed the answer, and the deterministic checks that ran. The manifest is written <em>before</em> a failed check raises, so the audit trail survives the error rather than disappearing with it.</p><p>Capabilities are reached through a searchable catalogue rather than a wall of tools, because a caller's ability to pick the right tool degrades long before a catalogue does. The catalogue answers with a set of candidates and the text that distinguishes them, not with a verdict.</p><p>A manifest records what was done; it does <em>not</em> certify that what was done was right. MapSmith says so in its own documentation, and a separate correctness suite exists to measure the difference.</p>"
+}