Context
MainFrame v0.3.0 evaluated the current standalone MindGraph source for a bounded public-core retrieval profile and deferred promotion after the clean-environment gate failed.
Frozen source under test:
- commit:
4d292179e1478b999bc6b7c36f9de564c07bd1d9
- tree:
ed7803dcf9718005fd190a12f0537b69dcb8b349
Primary qualification record:
Observed blockers
A clean GitHub-hosted Ubuntu / Python 3.11 installation of .[dev] succeeded, but pytest -q failed during collection before the synthetic ingest/query qualification could run.
Observed failures:
src/mindgraph/query.py references Literal without importing it, producing NameError during collection.mcp>=1.0.0 resolved to MCP 2.2.0, while the current tests import create_connected_server_and_client_session from mcp.shared.memory; that symbol is unavailable in the resolved version.tests/test_pruning.py imports pruning_pass, which is unavailable in the clean checkout/package environment.- The default dependency closure pulls
sentence-transformers, Torch, and a large Linux CUDA stack. That may be valid for the full semantic engine but is substantially heavier than the smallest MainFrame public retrieval profile needs.
These observations do not establish that MindGraph's retrieval architecture is unsound. They establish that this exact source does not currently reproduce cleanly enough to promote into MainFrame's public core.
Target
Create the smallest portable profile that can clear a clean-clone qualification without weakening the retrieval authority boundary.
At minimum, a successor gate should prove:
- clean supported-Python installation from the exact candidate;
- maintained tests collect and pass under pinned/supported dependency versions;
- fresh synthetic index creation with no pre-existing/private DB;
- query recovers the intended synthetic note;
- results preserve inspectable source provenance;
- unrelated/noise material remains distinguishable;
- querying before required index state fails clearly or closed;
- index deletion and rebuild reproduces stable result identity/provenance;
- retrieval output remains nomination only, not truth, verification, or lifecycle authority;
- the important bounded path is practical to run in public CI.
Scope guidance
For a future MainFrame promotion, prefer a slim closure first: core indexing/persistence/query/provenance, minimal CLI, synthetic fixtures, and meaningful CI. Treat semantic/vector retrieval as an optional extra if its dependency/model cost cannot be made proportionate. Daemon, shared MCP/proxy lifecycle, project federation, and repair tooling should not enter the MainFrame core merely because they exist in standalone MindGraph.
Do not change the historical MainFrame v0.2.0 implementation or reinterpret its release. A future promotion should use a newly qualified exact MindGraph candidate and then pass through MainFrame's private positive-manifest publication boundary.
Context
MainFrame v0.3.0 evaluated the current standalone MindGraph source for a bounded public-core retrieval profile and deferred promotion after the clean-environment gate failed.
Frozen source under test:
4d292179e1478b999bc6b7c36f9de564c07bd1d9ed7803dcf9718005fd190a12f0537b69dcb8b349Primary qualification record:
1016321546597f76a487d05a62f6ba2bdae40ad7a3d101597e077c5e230847b850dc00d4640Observed blockers
A clean GitHub-hosted Ubuntu / Python 3.11 installation of
.[dev]succeeded, butpytest -qfailed during collection before the synthetic ingest/query qualification could run.Observed failures:
src/mindgraph/query.pyreferencesLiteralwithout importing it, producingNameErrorduring collection.mcp>=1.0.0resolved to MCP 2.2.0, while the current tests importcreate_connected_server_and_client_sessionfrommcp.shared.memory; that symbol is unavailable in the resolved version.tests/test_pruning.pyimportspruning_pass, which is unavailable in the clean checkout/package environment.sentence-transformers, Torch, and a large Linux CUDA stack. That may be valid for the full semantic engine but is substantially heavier than the smallest MainFrame public retrieval profile needs.These observations do not establish that MindGraph's retrieval architecture is unsound. They establish that this exact source does not currently reproduce cleanly enough to promote into MainFrame's public core.
Target
Create the smallest portable profile that can clear a clean-clone qualification without weakening the retrieval authority boundary.
At minimum, a successor gate should prove:
Scope guidance
For a future MainFrame promotion, prefer a slim closure first: core indexing/persistence/query/provenance, minimal CLI, synthetic fixtures, and meaningful CI. Treat semantic/vector retrieval as an optional extra if its dependency/model cost cannot be made proportionate. Daemon, shared MCP/proxy lifecycle, project federation, and repair tooling should not enter the MainFrame core merely because they exist in standalone MindGraph.
Do not change the historical MainFrame v0.2.0 implementation or reinterpret its release. A future promotion should use a newly qualified exact MindGraph candidate and then pass through MainFrame's private positive-manifest publication boundary.