|
|
|
|
@@ -0,0 +1,34 @@
|
|
|
|
|
# Track Specification: Tiered Context Scoping & HITL Approval
|
|
|
|
|
|
|
|
|
|
## Overview
|
|
|
|
|
Provide the user with absolute visual control over what the AI sees at every level of the hierarchy. Currently, the system builds a single massive context blob. This track introduces context subsetting based on the target tier and implements a Human-in-the-Loop (HITL) approval gate before any Tier 3/4 worker is spawned.
|
|
|
|
|
|
|
|
|
|
## Goals
|
|
|
|
|
1. **Context Subsetting:** Modify the aggregation logic so that Tier 1, Tier 2, and Tier 3/4 receive distinct, optimized context packages.
|
|
|
|
|
2. **Spawn Interceptor:** Implement a `BeforeSpawn` hook mechanism within the application to pause execution right before a sub-agent is launched.
|
|
|
|
|
3. **Approval UX:** Design and implement a GUI modal that displays the exact prompt and context intended for the worker, allowing the user to Approve, Modify, or Reject the spawn.
|
|
|
|
|
|
|
|
|
|
## Constraints
|
|
|
|
|
- Must adhere to the project's security and transparency mandates.
|
|
|
|
|
- The interceptor must be reliable and not cause the main event loop to hang indefinitely.
|
|
|
|
|
|
|
|
|
|
## Context & Origins
|
|
|
|
|
This track was born from the "Human Verification" phase of the initial MMA Orchestrator prototype (`mma_orchestrator_integration_20260226`). We realized that while the backend API plumbing for the hierarchical MMA tiers (Tiers 1-4) was technically functional, the product lacked the necessary state management, UX visualization, and human-in-the-loop security gates to be usable.
|
|
|
|
|
|
|
|
|
|
**Key Takeaways from the Prototype Phase:**
|
|
|
|
|
- The Tier 2 (Tech Lead) needs its own track-scoped discussion history, rather than polluting the global project history.
|
|
|
|
|
- Tasks within a track require a DAG (Directed Acyclic Graph) engine to manage complex dependencies and blocking states.
|
|
|
|
|
- The GUI must visualize this DAG and stream the output of individual workers directly to their associated tasks.
|
|
|
|
|
- We must enforce tiered context subsetting so that Tier 3/4 workers don't receive the massive global context blob, and we need a pre-spawn approval modal so the user can intercept, review, and modify worker prompts/contexts before they execute.
|
|
|
|
|
|
|
|
|
|
**Instructions for the Implementing Agent:**
|
|
|
|
|
As you execute this track, ensure you maintain alignment with the other Phase 2 tracks. If you learn something that impacts the dependent tracks, please append a similar "Context Summary" to their `spec.md` files before concluding your run.
|
|
|
|
|
|
|
|
|
|
## Execution Order & Dependencies
|
|
|
|
|
This is a multi-track phase. To ensure architectural integrity, these tracks **MUST** be executed in the following strict order:
|
|
|
|
|
1. **MMA Data Architecture & DAG Engine:** (Builds the state and execution foundation)
|
|
|
|
|
2. **[CURRENT] Tiered Context Scoping & HITL Approval:** (Builds the security and context subsetting on top of the state)
|
|
|
|
|
3. **MMA Dashboard Visualization Overhaul:** (Builds the UI to visualize the state and subsets)
|
|
|
|
|
4. **Robust Live Simulation Verification:** (Builds the tests to verify the UI and state)
|
|
|
|
|
|
|
|
|
|
**Prerequisites for this track:** `MMA Data Architecture & DAG Engine` MUST be completed (`[x]`) before starting this track.
|