Skip to main content
Glama
Nitefawkes

MipCode

by Nitefawkes
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

MipCode (.mip / .mip.json) v0.4 — Architectural Mipmaps & Stateful Pre-Edit Guardrails for AI Coding Agents

Architectural Mipmaps + Stateful Pre-Edit Guardrails: Compile any polyglot repository (Rust, Python, TypeScript/JS) into a self-contained .mip.json (.mip) container with incremental SQLite caching, Stateful "Fog-of-War" Resolution Gating, Production-First Blast-Radius Analysis, and a Zero-Tax Compact Markdown Wire Protocol.

Why MipCode?

When coding agents modify complex repositories, two failure modes dominate:

  1. Context Starvation (Flat RepoMaps / Naive Lexical Search): Signature dumps and raw grep strip out project-level decisions (DEC-01), doc-comment invariants (//! INVARIANT), inline module constants, and cross-language coupling. The agent edits a signature or constant and triggers cascading regressions across uninspected callers.

  2. Context Overload (Verbose JSON / Raw File Dumps): Dumping entire files or repeating verbose JSON schemas and 64-character SHA-256 hashes per line exhausts tight agent token and byte budgets before the agent can inspect all affected callers.

MipCode v0.4 solves both by combining computer-graphics mipmapping (L0–L3), Stateful Fog-of-War resolution gating, and Active Pre-Edit Guardrails:

Mip Level

Resolution Name

Contents

Access & Guardrail Rule

L0

L0_WORLD_MAP

Active mission, decisions, global rules, and top modules ranked by coupling centrality within a strict token budget + exact l0_loss ledger.

Mounted first via mip.map() (mip_map).

L1

L1_BLUEPRINT

Public contracts, 3-tier epistemic rules (EXTRACTED_FACT, DECLARED_RULE, HEURISTIC_HAZARD), and cross-language coupling edges.

Required before L3 source edits (mip.verify_edit() / mip_verify_edit).

L2

L2_MECHANICS

Compact symbol signatures, line spans, outgoing calls, and symbol-filtered inline module constants.

Compact diet by default (-65.6% JSON byte reduction) via mip.zoom(target, "L2").

L3

L3_RAW_SOURCE

Exact 1-based line-numbered source slices + auto-inlined referenced constants unpacked from embedded zlib+base64 blobs and verified via live SHA-256 freshness checks.

Gated by Fog-of-War: Jumping straight to L3 or editing without L1/blast-radius hydration triggers an automatic guardrail interception.

Related MCP server: Hoplon

MCP Tool Namespace (mip.*)

Tool (mip.* / MCP Name)

Purpose

mip.map() (mip_map)

Mount budgeted L0_WORLD_MAP with top modules by centrality, project rules, and explicit l0_loss ledger.

mip.symbols() (mip_symbols)

Query the cross-language symbol & call-reference index across all mipmap levels.

mip.zoom() (mip_zoom)

Progressive L1 / L2 / L3 mipmap zoom with Stateful Fog-of-War gating and live SHA-256 freshness checks.

mip.blast() (mip_blast)

Transitive BFS blast-radius analysis ranking production callers ahead of test callers and separating executable calls from docstrings/prose/imports.

mip.guardrail() (mip_guardrail)

Single-call Pre-Edit Guardrail packet rendered in Compact Markdown (79%–86% smaller than JSON).

mip.verify_edit() (mip_verify_edit)

Host Pre-Edit Interception Hook (Claude Code PreToolUse / git pre-commit) enforcing L1 & blast-radius hydration before file writes.

mip.propose_delta() (mip_propose_delta)

Governed working-context writeback backed by cryptographic hydration receipts (rcpt_...).

(Legacy lod_* tool aliases and .lod.json containers remain supported for backward compatibility.)

Origins: Why Passive Multi-Resolution Summaries Weren't Enough

MipCode began as an empirical investigation into hierarchical context compression (often discussed conceptually as "Semantic LOD" or multi-resolution repo summaries). Across five heldout benchmark iterations (v0.1 $\rightarrow$ v0.4), we discovered that passive hierarchical text summaries alone fail as a replacement for rg + file reads:

  • Under equal byte budgets, verbose JSON multi-resolution schemas lose to fast lexical grep (rg) on pure navigation tasks.

  • Coding agents routinely ignore passive expand_when advisory hints when rushing to patch a file.

What actually moved first-attempt cross-module refactoring pass rates from 0% to 100% was replacing passive summaries with MipCode's active guardrail architecture:

  1. Stateful "Fog-of-War" Session Gating & Pre-Edit Hooks (mip.verify_edit / mip.guardrail) that actively intercept blind edits (exit_code=2 / exit_code=3) and auto-hydrate missing contracts and blast-radius callers.

  2. Three-Tier Epistemic Typing (EXTRACTED_FACT, DECLARED_RULE, HEURISTIC_HAZARD) + explicit omission accounting (l0_loss, omitted_at_l1).

  3. Production-First Blast Radius (mip.blast) separating genuine executable call sites from docstring/comment prose mentions and import statements.

  4. Zero-Tax Compact Markdown Wire Protocol (render_compact_markdown) cutting agent wire overhead by 79%–86% while preserving internal SHA-256 provenance.

Quick Start

1. Install

pip install -e .
# Optional: enable native Tree-Sitter AST backend and MCP SDK
pip install -e ".[ast,mcp]"

2. Compile a .mip.json Container (Full or Incremental)

python -m mipcode.compiler demo_engine 500 --mip --incremental

3. Run the Pre-Edit Guardrail Audit on Any Repository

python -m mipcode.real_repo_deploy demo_engine sym://src/projection.rs#OwnedProposal --markdown

4. Run the Full Multi-Condition Benchmark Suite

python -m mipcode.benchmark demo_engine --live-agent

License

Apache License 2.0 — Copyright 2026 Brian Gansz. See LICENSE.

This server cannot be deployed

Shareable, User-Owned Context BackendPeople, applications, and agents read, write, and coordinate together in one context lake. Reach it over MCP, a CLI, a Python SDK, or REST.fulcradynamics.comAd

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • Manifold Engine MCP Server

    SepDynamics
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables AI coding assistants to perform high-speed structural codebase analysis and dynamic context management by mapping repositories as byte-streams and detecting architectural chaos.
    MIT

  • Hoplon

    justguy
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables AI coding agents and hosts to enforce deterministic repository boundaries via MCP, providing structured reads, supervised edits, snapshots, audits, and recovery with machine-readable evidence.
    MIT

  • onto-agent

    rinDBeans
    A
    license
    Not graded
    quality
    A
    maintenance
    Provides AI coding agents with an embedded knowledge graph and architecture governance tools, enabling blast radius analysis, compliance checks, and smart context extraction from codebases.
    Apache 2.0

  • openkrak-mcp

    FrnzJulianBergmann
    F
    license
    Not graded
    quality
    B
    maintenance
    Enables coding agents to pre-compute repository structure and access structured intelligence briefs, including dependency graphs, hotspots, and blast radius, reducing token usage and improving code understanding.
    55 npm
    1
    -