v0.7.3

Changes

• feat: ModelRef gains a metadata: dict[str, Any] field (default empty). Thread through register() and register_group().
• feat: register_group(metadata=...) now stores metadata on the composite ModelRef itself. Previously broadcast to every link_dependency call (unintended).
• feat: composite_summary(model_types=...) — optional filter for callers treating ml_model/heuristic (or other types) as composites. Default behavior preserved (model_type="composite").
• fix: narrow ALTER TABLE ADD COLUMN METADATA VARIANT exception suppression to "already exists" only. Previously swallowed all DDL errors.
• schema: SQLite + Snowflake backends carry a METADATA column. Existing deployments auto-migrate via idempotent ALTER TABLE.

Backward compatibility

Fully backward compatible. Existing serialized ModelRef data without a metadata field loads with metadata={}.

Upgrade

pip install -U model-ledger==0.7.3

Or for git-pinned consumers:

model-ledger = { git = "https://github.com/block/model-ledger.git", tag = "v0.7.3" }

v0.7.2

• Push limit, offset, text filters to SQL in Snowflake backend — avoids S3 result downloads for paginated queries
• Add count_models() for efficient total counts
• In-memory backend also supports text/limit/offset for parity
• Fixes 403 errors when querying through corporate proxies that break S3 presigned URLs

v0.7.1

• Add read_only=True parameter to SnowflakeLedgerBackend — skips CREATE SCHEMA/TABLE for service accounts with SELECT-only access

v0.7.0

What's New

• HTTP backend — connect MCP clients to a remote REST API without direct database credentials
• Snowflake & HTTP backends in CLI — model-ledger mcp --backend snowflake and --backend http
• MCP pass-through mode — MCP server delegates to REST API when using HTTP backend

Fixes

• Fresh release to resolve corrupted proxy cache hashes from v0.6.x

v0.6.1

What's New

• HTTP backend — connect MCP clients to a remote REST API without direct database credentials
• Snowflake & HTTP backends in CLI — model-ledger mcp --backend snowflake and --backend http
• MCP pass-through mode — MCP server delegates to REST API when using HTTP backend
• Fix wheel metadata for PyPI distribution

v0.6.0 — Agent-first protocol

What's New

Agent-first model inventory. model-ledger now ships an MCP server, REST API, and 6 consolidated tools — designed for AI agents to interact with your model inventory.

Quick Start

pip install model-ledger[mcp]
claude mcp add model-ledger -- model-ledger mcp --demo

6 Agent Tools

Tool	What it does
discover	Add models from any source — scan platforms, import files, inline data
record	Register a model or record an event with arbitrary metadata
investigate	Deep dive — identity, metadata, events, dependencies
query	Search and filter the inventory with pagination
trace	Dependency graph — upstream, downstream, impact analysis
changelog	What changed across the inventory in a time range

New Features

• MCP server — model-ledger mcp starts a stdio server for Claude Code and any MCP-compatible agent
• REST API — model-ledger serve starts FastAPI with auto-generated OpenAPI docs at /docs
• JSON file backend — human-readable, git-friendly default storage
• Demo mode — --demo flag loads 7 sample models with events and dependencies
• 198 new tests (573 total)

Install Profiles

pip install model-ledger            # Core
pip install model-ledger[mcp]       # + MCP server
pip install model-ledger[rest-api]  # + REST API
pip install model-ledger[snowflake] # + Snowflake backend

Full Changelog: v0.5.0...v0.6.0

v0.5.0

Full Changelog: https://github.com/block/model-ledger/commits/v0.5.0