Skip to content

Zekiog verified memory repo shortlist plan#89

Open
Zekiog wants to merge 7 commits into
LLMQuant:masterfrom
Zekiog:zekiog-verified-memory-repo-shortlist-plan
Open

Zekiog verified memory repo shortlist plan#89
Zekiog wants to merge 7 commits into
LLMQuant:masterfrom
Zekiog:zekiog-verified-memory-repo-shortlist-plan

Conversation

@Zekiog

@Zekiog Zekiog commented Jul 7, 2026

Copy link
Copy Markdown

Description

Checklist

Please feel free to remove inapplicable items for your PR.

  • The PR title starts with $CATEGORY(xx): xxx (such as feat(tool): xxx, fix(source): xxx, docs(README): xxx)
  • Related issue is referred in this PR
  • The markdown and latex are rendered correctly.
  • The code in PR is well-documented.
  • The PR is complete and small, read the Google eng practice (CL equals to PR) to understand more about small PR.

Zekiog and others added 6 commits June 15, 2026 17:17
Documents the QuantMind ↔ fincept-ai-ops architecture:
- Vector search over quantitative finance literature
- MCP tool schema for knowledge queries
- Factor library synergy with backtest strategies
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot AI review requested due to automatic review settings July 7, 2026 23:11

Copilot AI left a comment

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull request overview

This PR expands QuantMind’s “durable loop” direction by introducing governance policy primitives (YAML + runtime helpers), adding an initial hybrid memory engine (L1/L2/L3), and documenting the updated agent-centric positioning with new examples and tests.

Changes:

  • Add governance policy schema + loader + enforcement helpers (quantmind/flows/governance.*) and wire optional tool-allowlist checks into magic.resolve_magic_input(...).
  • Introduce initial “mind” layer primitives (HybridMemoryEngine, L3 commit gates) plus recoverable validation utilities for tolerant ingestion.
  • Refresh repo docs (README/CONTRIBUTING/architecture) and add tests/examples for the new modules.

Reviewed changes

Copilot reviewed 20 out of 22 changed files in this pull request and generated 7 comments.

Show a summary per file
File Description
tests/test_magic.py Adds integration tests for resolver-side governance enforcement.
tests/mind/test_memory.py Adds tests for L1/L2 writes and L3 commit gating behavior.
tests/mind/init.py Establishes tests.mind package namespace.
tests/flows/test_governance.py Adds unit tests for governance loader, allowlists, loop budgets, fallback policy, and L3 gates.
tests/configs/test_recoverable.py Adds tests for recoverable validation returning either strict models or fallback nodes.
README.md Repositions project messaging and documents governance/memory direction and usage.
quantmind/mind/memory.py Implements filesystem-backed hybrid memory primitives and L3 commit gates.
quantmind/mind/init.py Exposes mind public API surface.
quantmind/magic.py Adds optional governance parameters and tool allowlist checks to the resolver path.
quantmind/flows/governance.yaml Defines default governance policy (loop budget, fallback, tool allowlists, L3 gates).
quantmind/flows/governance.py Adds governance policy models + loader + enforcement helpers.
quantmind/flows/init.py Re-exports governance helpers from the flows apex package.
quantmind/configs/recoverable.py Adds recoverable validation helper and structured fallback node model.
quantmind/configs/init.py Exports recoverable validation types from the configs surface.
quantmind/init.py Updates package-level description to match agentic workflow focus.
examples/mind/recoverable_memory_demo.py Demonstrates recoverable ingestion and gated memory commit.
draft_corrections.md Adds draft notes for “verified memory repo shortlist” work.
docs/fincept_integration.md Adds Fincept integration guide (currently references non-existent API/CLI).
docs/ARCHITECTURE_FOR_NEW_DOMAINS.md Adds guidance for extending QuantMind beyond the initial paper domain.
CONTRIBUTING.md Updates contributor guidance to match current architecture + verification loop.
.impeccable/hook.cache.json Adds a tool cache artifact (should not be committed).
.gitignore Adds .venv/ ignore (and should also ignore .impeccable/).
Files not reviewed (1)
  • .impeccable/hook.cache.json: Generated file

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment thread README.md
Comment thread docs/fincept_integration.md
Comment thread tests/configs/test_recoverable.py
Comment thread tests/flows/test_governance.py
Comment thread quantmind/flows/governance.py
Comment thread .impeccable/hook.cache.json
Comment thread docs/fincept_integration.md Outdated
Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants