arangodb-schema-analyzer 0.3.0__tar.gz

arangodb_schema_analyzer-0.3.0/.gitignore

@@ -0,0 +1,43 @@
+# Python
+__pycache__/
+*.py[cod]
+*.pyd
+*.so
+.Python
+build/
+dist/
+*.egg-info/
+.eggs/
+
+# Virtual environments
+.venv/
+.venv-*/
+venv/
+env/
+
+# Build / packaging
+dist/
+wheels/
+
+# Test / tooling
+.pytest_cache/
+.mypy_cache/
+.ruff_cache/
+.coverage
+coverage.xml
+
+# OS / editor
+.DS_Store
+.idea/
+.vscode/
+
+# Project-specific
+.schema-analyzer-cache/
+.env
+.env.*
+!.env.example
+
+# Eval outputs
+eval_report*.json
+eval_*.json
+

arangodb_schema_analyzer-0.3.0/CHANGELOG.md

@@ -0,0 +1,129 @@
+# Changelog
+
+## 0.3.0
+
+First PyPI release. Consolidates the quality + contract work originally
+slated for `0.2.0` (issues #2-#6) with the cheap schema-change probes
+(#7) and PRD amendment (#8) that landed on `main` shortly after.
+Version `0.2.0` was prepared on `main` but never published; `0.3.0` is
+the first tag to reach PyPI.
+
+### Tool contract changes (breaking)
+
+- **#6 key rename.** Property mappings now emit `field` (was
+  `physicalFieldName`). Relationship mappings now emit
+  `edgeCollectionName` and MUST NOT emit `collectionName` — the JSON
+  schema rejects the latter. Entity mappings still use
+  `collectionName` (unchanged). See `tool_contract/v1/response.schema.json`.
+  Consumers that previously ran a `_normalize_analyzer_pm` /
+  `_normalize_props` shim can delete it.
+
+### New features
+
+- **#7 cheap schema-change probes.** Two new top-level helpers in
+  `schema_analyzer.snapshot` (re-exported from the package root):
+  - `fingerprint_physical_shape(db, *, exclude_collections=None)` — hashes
+    only the user-collection set, per-collection type (document vs edge),
+    and per-collection sorted index digests (`type`, `fields`, `unique`,
+    `sparse`, `vci`, `deduplicate`). Auto-generated index `name` / `id`
+    are excluded so restarts and rebuilds don't produce false positives.
+    Stable under ordinary INSERT / UPDATE / REMOVE writes.
+  - `fingerprint_physical_counts(db, *, exclude_collections=None)` —
+    shape fingerprint combined with `col.count()` per included
+    collection; changes whenever the shape or any row count changes.
+  Both probes read only python-arango primitives (`db.collections()`,
+  `col.indexes()`, `col.count()`) — no AQL, no samples, no analyzer
+  logic — so consumers can answer "has it changed?" in a few dozen
+  milliseconds instead of running the full `snapshot_physical_schema`.
+  Collection-level failures degrade gracefully (sentinel contribution)
+  rather than raising. `exclude_collections` lets callers using a
+  database-resident cache self-exclude their bookkeeping collection.
+- **#3 statistics block.** `AgenticSchemaAnalyzer` now stamps
+  `metadata.statistics` with per-collection counts, per-entity
+  `estimated_count`, and a per-relationship bundle of `edge_count`,
+  `source_count`, `target_count`, `avg_out_degree`, `avg_in_degree`,
+  `cardinality_pattern` (`1:1` / `1:N` / `N:1` / `N:M`) and
+  `selectivity`. When no live DB is available
+  `metadata.statistics_status = "skipped_no_db"` and `statistics` is
+  absent. Bounded AQL cost: one `LENGTH` per collection, one filtered
+  `COLLECT` per LABEL / GENERIC_WITH_TYPE subset.
+- **#5 reconciliation step.** After the LLM returns, the analyzer
+  diffs its collection coverage against the snapshot and backfills any
+  missing collections via baseline inference. The merge is reported in
+  `metadata.reconciliation` with `llm_covered_collections`,
+  `snapshot_collections`, `backfilled_collections`, and `strategy`; a
+  user-visible warning is appended. No-op when the LLM's output is
+  already complete.
+
+### Quality
+
+- **#4 discriminator hardening.** `_pick_best_type_field` now rejects
+  candidate type fields that look like identifiers (`*Id`, `*_id`,
+  `uuid`, etc.), carry too many distinct values
+  (`MAX_TYPE_FIELD_DISTINCT_VALUES=32`), or cover too little of the
+  collection (`MIN_TYPE_FIELD_COVERAGE_FRACTION=0.80`). Single-distinct-
+  value edge discriminators are still accepted under the
+  single-value-edge fallback. New tunables live in `defaults.py`.
+- **#2 richer index flags.** `physicalMapping[...].indexes[*]` now
+  propagates `vci`, `deduplicate`, and `storedValues` from the raw
+  ArangoDB index metadata. Vertex-Centric Indexes are excluded from the
+  `indexed=True` heuristic on properties.
+
+### Documentation
+
+- **#8 PRD §3.13.3 / §4.1 update.** The PRD now sanctions the two-
+  fingerprint model (shape vs counts), a four-state change-status
+  contract (`unchanged` / `stats_changed` / `shape_changed` /
+  `no_cache`), stats-only refresh as the product behavior for
+  `stats_changed`, storage-agnostic caching, and self-exclusion of
+  database-resident cache collections from the shape fingerprint.
+
+### CI / Release infrastructure
+
+- Trusted-publisher GitHub Actions workflow (`publish.yml`) targeting
+  PyPI and TestPyPI via OIDC — no long-lived tokens.
+- `sdist` allow-list tightened in `pyproject.toml` so source
+  distributions include only package code, licence, readme, changelog,
+  and the tool-contract JSON schemas.
+- `schema_analyzer/py.typed` added so downstream type checkers pick up
+  the package's inline annotations.
+- Ruff lint + format are enforced by CI; mypy runs in advisory mode.
+
+## 0.2.0 (never published)
+
+`0.2.0` was bumped on `main` as the planned first PyPI release but the
+tag was never cut — #7 and #8 landed before release and the scope was
+rolled forward into `0.3.0`. Everything originally slated for `0.2.0`
+is part of `0.3.0` above.
+
+## 0.1.0
+
+### Initial release
+
+- Physical schema snapshotting with deterministic ordering and fingerprinting
+- Conceptual schema inference (entities, relationships, properties)
+- Physical mapping generation (COLLECTION, LABEL, DEDICATED_COLLECTION, GENERIC_WITH_TYPE)
+- AQL fragment helpers (`aql_entity_match`, `aql_relationship_traversal`) with injection-safe bind parameters
+- LLM-assisted analysis with generate → validate → repair loop
+- Provider support: OpenAI, Anthropic, OpenRouter (pluggable registry)
+- Deterministic baseline inference when no LLM is configured (graceful degradation)
+- Filesystem caching keyed by schema fingerprint with configurable TTL
+- Tool contract v1: stable JSON API (stdin/stdout) with request/response schema validation
+- CLI: tool mode (stdin JSON) and eval subcommand
+- Output formats: analysis JSON, snapshot, export (Cypher), Markdown docs, OWL Turtle
+- Evaluation harness with 5 domain packs, physical schema generator, and F1/accuracy scoring
+- Eval report comparison for tracking quality regressions
+
+### Quality improvements
+
+- Centralized tunable defaults in `defaults.py` (LLM parameters, timeouts, confidence, cache)
+- Unified `pascal_case()` utility replacing duplicate implementations
+- Shared test helpers extracted into `conftest.py`
+- Consolidated sync/async workflow via shared `_parse_and_validate()` helper
+- Catch-all error handler in tool entrypoint for contract-shaped error responses
+- Eliminated redundant snapshot work (tool passes pre-built snapshot to analyzer)
+- TYPE_CHECKING guards for `StandardDatabase` imports
+- Proper exception chaining (`raise ... from e`) across all providers and workflow
+- Logging in tool.py (operation tracking) and cache.py (corrupt file warnings)
+- CI: pip caching, integration tests trigger on PRs, coverage threshold at 65%
+- Test coverage for: cache, docs, exports, OWL export, validation, providers, conceptual schema, CLI, tool happy paths

arangodb_schema_analyzer-0.3.0/CONTRIBUTING.md

@@ -0,0 +1,97 @@
+# Contributing
+
+## Development setup
+
+```bash
+python -m venv .venv
+source .venv/bin/activate
+python -m pip install -U pip
+python -m pip install -e ".[dev]"
+```
+
+## Running tests
+
+```bash
+# Unit tests (default)
+pytest -q
+
+# With verbose output
+pytest -v
+
+# Integration tests (requires Docker ArangoDB on port 18529)
+docker compose up -d
+export RUN_INTEGRATION=1
+export ARANGO_URL=http://localhost:18529
+export ARANGO_DB=schema_analyzer_it
+export ARANGO_USER=root
+export ARANGO_PASS=openSesame
+pytest -q -m integration
+```
+
+## Linting and formatting
+
+```bash
+ruff check .           # lint
+ruff format --check .  # format check
+ruff format .          # auto-format
+mypy schema_analyzer/  # type checking
+```
+
+## Project structure
+
+```
+schema_analyzer/
+├── analyzer.py          # AgenticSchemaAnalyzer (main entry point)
+├── baseline.py          # Deterministic inference (no LLM fallback)
+├── cache.py             # Filesystem caching by schema fingerprint
+├── cli.py               # CLI: tool mode + eval subcommand
+├── conceptual.py        # ConceptualSchema dataclass
+├── defaults.py          # Centralized tunable constants
+├── docs.py              # Markdown documentation generator
+├── errors.py            # SchemaAnalyzerError
+├── exports.py           # Transpiler export (Cypher)
+├── mapping.py           # PhysicalMapping with AQL helpers
+├── owl_export.py        # OWL Turtle export
+├── snapshot.py          # Physical schema introspection
+├── tool.py              # Tool contract v1 entrypoint
+├── tool_contract_v1.py  # JSON Schema validation
+├── types.py             # Pydantic models (AnalysisMetadata, AnalysisResult)
+├── utils.py             # Shared utilities (pascal_case, sha256, JSON extraction)
+├── validation.py        # LLM output validation schema
+├── workflow.py          # Generate → validate → repair loop
+├── eval/                # Evaluation harness
+│   ├── domain_loader.py # Load domain specs from domains/
+│   ├── generator.py     # Physical schema generator (PG + LPG variants)
+│   ├── runner.py        # Eval orchestration and reporting
+│   └── scoring.py       # F1, domain/range, mapping style scoring
+├── providers/           # LLM provider implementations
+│   ├── base.py          # LLMProvider protocol
+│   ├── openai_provider.py
+│   ├── anthropic_provider.py
+│   └── openrouter_provider.py
+└── tool_contract/v1/    # Bundled JSON Schema files
+```
+
+## Guidelines
+
+- Keep outputs deterministic (ordering, stable JSON).
+- Do not log or persist secrets (API keys, credentials).
+- Add/adjust tests for behavior changes (golden fixtures where appropriate).
+- Use `defaults.py` for tunable constants — avoid scattering magic numbers.
+- Use `pascal_case()` from `utils.py` — do not create local copies.
+- Shared test helpers live in `tests/conftest.py` — prefer importing over duplicating.
+- Provider implementations should use `raise ... from e` for proper exception chaining.
+- All tool responses (including unexpected errors) must be contract-shaped JSON.
+
+## Adding a new LLM provider
+
+1. Create `schema_analyzer/providers/my_provider.py` implementing the `LLMProvider` protocol
+2. Register in `schema_analyzer/providers/__init__.py` `_REGISTRY`
+3. Use constants from `defaults.py` for temperature, max_tokens, etc.
+4. Wrap SDK errors as `SchemaAnalyzerError(code="PROVIDER_ERROR")` with `raise ... from e`
+
+## Adding a new domain pack
+
+1. Create `domains/<name>/domain.json` with entities and relationships
+2. The eval harness auto-discovers domains via `list_domains()`
+3. Run `arangodb-schema-analyzer eval --domains <name>` to test

arangodb_schema_analyzer-0.3.0/LICENSE

@@ -0,0 +1,174 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+

arangodb_schema_analyzer-0.3.0/PKG-INFO

@@ -0,0 +1,198 @@
+Metadata-Version: 2.4
+Name: arangodb-schema-analyzer
+Version: 0.3.0
+Summary: Agentic schema analyzer for ArangoDB: conceptual model + conceptual-to-physical mapping for transpilers.
+Project-URL: Homepage, https://github.com/ArthurKeen/arango-schema-mapper
+Project-URL: Repository, https://github.com/ArthurKeen/arango-schema-mapper
+Project-URL: Issues, https://github.com/ArthurKeen/arango-schema-mapper/issues
+Project-URL: Changelog, https://github.com/ArthurKeen/arango-schema-mapper/blob/main/CHANGELOG.md
+Author: Arthur Keen
+Maintainer: Arthur Keen
+License-Expression: Apache-2.0
+License-File: LICENSE
+Keywords: arangodb,conceptual-model,cypher,graph,llm,mcp,ontology,owl,schema,sparql,transpiler
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Information Technology
+Classifier: Operating System :: OS Independent
+Classifier: Programming Language :: Python
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3 :: Only
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Classifier: Topic :: Database
+Classifier: Topic :: Scientific/Engineering :: Information Analysis
+Classifier: Topic :: Software Development :: Libraries :: Python Modules
+Classifier: Typing :: Typed
+Requires-Python: >=3.10
+Requires-Dist: jsonschema>=4.21.0
+Requires-Dist: pydantic>=2.6.0
+Requires-Dist: python-arango>=8.1.1
+Provides-Extra: anthropic
+Requires-Dist: anthropic>=0.25.0; extra == 'anthropic'
+Provides-Extra: dev
+Requires-Dist: mypy>=1.10.0; extra == 'dev'
+Requires-Dist: pytest-cov>=5.0.0; extra == 'dev'
+Requires-Dist: pytest>=8.0.0; extra == 'dev'
+Requires-Dist: ruff>=0.4.0; extra == 'dev'
+Provides-Extra: mcp
+Requires-Dist: mcp>=1.2.0; extra == 'mcp'
+Provides-Extra: openai
+Requires-Dist: openai>=1.0.0; extra == 'openai'
+Provides-Extra: openrouter
+Description-Content-Type: text/markdown
+
+# arangodb-schema-analyzer (v0.1)
+
+Standalone Python library that analyzes an ArangoDB database's physical schema and produces:
+
+- a **conceptual schema** (entities, relationships, properties)
+- a **conceptual→physical mapping** suitable for transpilers (Cypher, SPARQL, future)
+- **metadata** (confidence, timestamp, analyzed collection counts, detected patterns)
+
+## Install
+
+From source (this repo):
+
+```bash
+python -m pip install -e .
+```
+
+Optional LLM provider extras:
+
+```bash
+python -m pip install -e ".[openai]"
+python -m pip install -e ".[anthropic]"
+```
+
+OpenRouter is also supported and requires no extra SDK (uses stdlib `urllib`).
+
+**MCP (Model Context Protocol)** — optional stdio server wrapping the v1 JSON tool contract:
+
+```bash
+python -m pip install -e ".[mcp]"
+arangodb-schema-analyzer-mcp
+```
+
+If you don't install a provider SDK (or you don't provide an API key), analysis degrades gracefully to deterministic baseline inference.
+
+## Usage
+
+```python
+from arango import ArangoClient
+
+from schema_analyzer import AgenticSchemaAnalyzer
+
+client = ArangoClient(hosts="http://localhost:8529")
+db = client.db("mydb", username="root", password="openSesame")
+
+analyzer = AgenticSchemaAnalyzer(
+    llm_provider="openai",  # or "anthropic" or "openrouter"
+    api_key=None,           # e.g. os.environ["OPENAI_API_KEY"]
+    model="gpt-4o-mini",
+    cache={"type": "filesystem", "directory": ".schema-analyzer-cache"},
+)
+
+analysis = analyzer.analyze_physical_schema(
+    db,
+    timeout_ms=60_000,
+    sample_limit_per_collection=5,
+)
+
+print(analysis.metadata.confidence)
+```
+
+## Tool usage (CLI)
+
+This project can be called as a **non-interactive tool** (stdin JSON → stdout JSON) using the v1 contract under `docs/tool-contract/v1/`.
+
+Install (editable):
+
+```bash
+python -m pip install -e .
+```
+
+Example (analyze) using the provided request example:
+
+```bash
+cat docs/tool-contract/v1/examples/request.analyze.json | arangodb-schema-analyzer --pretty
+```
+
+### CLI options
+
+```
+arangodb-schema-analyzer [--request FILE] [--out FILE] [--pretty] [-v]
+```
+
+- `--request FILE` — path to request JSON (default: read from stdin)
+- `--out FILE` — write response JSON to file (default: stdout)
+- `--pretty` — pretty-print JSON output
+- `-v` — enable verbose logging
+
+## Evaluation CLI
+
+Run analysis quality benchmarks against domain packs:
+
+```bash
+arangodb-schema-analyzer eval \
+  --provider openai \
+  --model gpt-4o-mini \
+  --report eval_report.json \
+  --baseline eval_baseline.json
+```
+
+Options: `--url`, `--user`, `--password`, `--database`, `--domains`, `--sample-limit`, `--timeout-ms`, `--scale`, `--no-cleanup`.
+
+Domains included: `healthcare`, `financial_fraud_detection`, `insurance`, `intelligence`, `network_asset_management`.
+
+## Public API
+
+Exports:
+
+- `AgenticSchemaAnalyzer` — main analyzer class
+- `ConceptualSchema` — conceptual schema dataclass
+- `PhysicalMapping` — physical mapping dataclass with AQL helpers
+- `generate_schema_docs(analysis)` — Markdown documentation generator
+- `export_mapping(analysis, target)` — transpiler export (v0.1: `cypher`)
+- `export_conceptual_model_as_owl_turtle(analysis)` — OWL Turtle export
+- `register_provider(name, ...)` — register custom LLM providers
+- `list_providers()` — list registered LLM provider names
+
+## Configuration
+
+Tunable defaults live in `schema_analyzer/defaults.py`. Key parameters:
+
+| Parameter | Default | Description |
+|---|---|---|
+| `MAX_REPAIR_ATTEMPTS` | 2 | LLM repair loop iterations |
+| `LLM_TEMPERATURE` | 0.0 | Sampling temperature |
+| `DEFAULT_TIMEOUT_MS` | 60000 | Analysis timeout (ms) |
+| `DEFAULT_REVIEW_THRESHOLD` | 0.6 | Confidence threshold for `review_required` |
+| `DEFAULT_CACHE_TTL_SECONDS` | 86400 | Cache TTL (seconds) |
+
+## Notes
+
+- **Secrets**: API keys are read from config/env; never persisted by this library.
+- **AQL fragments**: helper methods return AQL text + bind variables; collection names are passed via bind parameters.
+- **Graceful degradation**: without an LLM provider, the analyzer returns deterministic baseline inference with `review_required=True`.
+
+## Integration evaluation (Docker ArangoDB)
+
+Bring up a local ArangoDB:
+
+```bash
+docker compose up -d
+```
+
+Run integration tests (opt-in):
+
+```bash
+export RUN_INTEGRATION=1
+export ARANGO_URL=http://localhost:18529
+export ARANGO_DB=schema_analyzer_it
+export ARANGO_USER=root
+export ARANGO_PASS=openSesame
+pytest -q -m integration
+```