chore(conductor): Archive track 'tiered_context_scoping_hitl_approval'

This commit is contained in:
2026-02-27 23:05:06 -05:00
parent 24c46b8934
commit b1fdcf72c5
4 changed files with 0 additions and 0 deletions

View File

@@ -0,0 +1,7 @@
# Tiered Context Scoping & HITL Approval
Introduces context subsetting per tier and Human-in-the-Loop spawn interceptor logic.
### Navigation
- [Specification](./spec.md)
- [Implementation Plan](./plan.md)

View File

@@ -0,0 +1,6 @@
{
"id": "tiered_context_scoping_hitl_approval",
"title": "Tiered Context Scoping & HITL Approval",
"status": "planned",
"created_at": "2026-02-27T19:20:00.000000"
}

View File

@@ -0,0 +1,17 @@
# Implementation Plan: Tiered Context Scoping & HITL Approval
## Phase 1: Context Subsetting [checkpoint: d7a24d6]
- [x] Task: Refactor `aggregate.py` to support targeted context builds (e.g., `build_tier1_context`, `build_tier3_context`). 6aa642b
- [x] Task: Integrate AST skeleton extraction into the standard Tier 3 context build. 0ed01aa
- [x] Task: Update the project state to track which files are assigned to which tier. 2ece9e1
## Phase 2: The Spawn Interceptor [checkpoint: 4c53ca1]
- [x] Task: Create a signaling mechanism in `multi_agent_conductor.py` to emit a "Worker Spawn Requested" event. e293c5e
- [x] Task: Implement the interception logic that pauses the async dispatcher until a signal is received from the GUI. 4c53ca1
## Phase 3: Approval UX Modal [checkpoint: 21157f9]
- [x] Task: Design the "Approve Worker Spawn" modal in DearPyGui. 21157f9
- [x] Task: Populate the modal with the target role, the exact prompt, and a read-only view of the specific file context. 21157f9
- [x] Task: Wire the "Approve", "Modify", and "Reject" buttons to resume or cancel the intercepted spawn. 21157f9
## Phase: Review Fixes
- [x] Task: Apply review suggestions 82f73e7

View File

@@ -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.