checkpoint: fix regression when using gemini cli outside of manual slop.

conductor/tracks.md

@@ -46,3 +46,8 @@ This file tracks all major tracks for the project. Each track has its own detail
 ---
 
 
+
+---
+
+- [ ] **Track: Improve conductors use of 4-tier mma architecture workflow, skills, subagents. Introduce a seaprate skill for each dedicated tier and a dedicated cli tool to execute the roles appropriate/gather context as defined for that role's domain.**
+*Link: [./tracks/mma_formalization_20260225/](./tracks/mma_formalization_20260225/)*

conductor/tracks/mma_formalization_20260225/index.md

@@ -0,0 +1,5 @@
+# Track mma_formalization_20260225 Context
+
+- [Specification](./spec.md)
+- [Implementation Plan](./plan.md)
+- [Metadata](./metadata.json)

conductor/tracks/mma_formalization_20260225/metadata.json

@@ -0,0 +1,8 @@
+{
+  "track_id": "mma_formalization_20260225",
+  "type": "feature",
+  "status": "new",
+  "created_at": "2026-02-25T18:48:00Z",
+  "updated_at": "2026-02-25T18:48:00Z",
+  "description": "Improve conductors use of 4-tier mma architecture workflow, skills, subagents. Introduce a seaprate skill for each dedicated tier and a dedicated cli tool to execute the roles appropriate/gather context as defined for that role's domain."
+}

conductor/tracks/mma_formalization_20260225/plan.md

@@ -0,0 +1,27 @@
+# Implementation Plan: 4-Tier MMA Architecture Formalization
+
+## Phase 1: Tiered Skills Implementation
+- [ ] Task: Create `mma-tier1-orchestrator` skill in `.gemini/skills/`
+- [ ] Task: Create `mma-tier2-tech-lead` skill in `.gemini/skills/`
+- [ ] Task: Create `mma-tier3-worker` skill in `.gemini/skills/`
+- [ ] Task: Create `mma-tier4-qa` skill in `.gemini/skills/`
+- [ ] Task: Conductor - User Manual Verification 'Phase 1: Tiered Skills Implementation' (Protocol in workflow.md)
+
+## Phase 2: `mma-exec` CLI - Core Scoping
+- [ ] Task: Scaffold `scripts/mma_exec.py` with basic CLI structure (argparse/click)
+- [ ] Task: Implement Role-Scoped Document selection logic (mapping roles to `product.md`, `tech-stack.md`, etc.)
+- [ ] Task: Implement the "Context Amnesia" bridge (ensuring a fresh subprocess session for each call)
+- [ ] Task: Integrate `mma-exec` with the existing `ai_client.py` logic
+- [ ] Task: Conductor - User Manual Verification 'Phase 2: mma-exec CLI - Core Scoping' (Protocol in workflow.md)
+
+## Phase 3: Advanced Context Features
+- [ ] Task: Implement AST "Skeleton View" generator using `tree-sitter` in `scripts/mma_exec.py`
+- [ ] Task: Add dependency mapping to `mma-exec` (providing skeletons of imported files to Workers)
+- [ ] Task: Implement logging/auditing for all role hand-offs in `logs/mma_delegation.log`
+- [ ] Task: Conductor - User Manual Verification 'Phase 3: Advanced Context Features' (Protocol in workflow.md)
+
+## Phase 4: Workflow & Conductor Integration
+- [ ] Task: Update `conductor/workflow.md` with new MMA role definitions and `mma-exec` commands
+- [ ] Task: Create a Conductor helper/alias in `scripts/` to simplify manual role triggering
+- [ ] Task: Final end-to-end verification using a sample feature implementation
+- [ ] Task: Conductor - User Manual Verification 'Phase 4: Workflow & Conductor Integration' (Protocol in workflow.md)

conductor/tracks/mma_formalization_20260225/spec.md

@@ -0,0 +1,43 @@
+# Specification: 4-Tier MMA Architecture Formalization
+
+## Overview
+This track aims to formalize and automate the 4-Tier Hierarchical Multi-Model Architecture (MMA) within the Conductor framework. It introduces specialized skills for each tier and a new specialized CLI tool (`mma-exec`) to handle role-specific context gathering and "Context Amnesia" protocols.
+
+## Goals
+- Isolate cognitive load for sub-agents by providing only domain-specific context.
+- Minimize token burn through "Context Amnesia" and AST-based skeleton views.
+- Formalize the Orchestrator (Tier 1), Tech Lead (Tier 2), Worker (Tier 3), and QA (Tier 4) roles.
+
+## Functional Requirements
+
+### 1. Specialized Tier Skills
+Create four new Gemini CLI skills located in `.gemini/skills/`:
+- **mma-tier1-orchestrator:** Focused on product alignment, high-level planning, and track management.
+- **mma-tier2-tech-lead:** Focused on architectural design, tech stack alignment, and code review.
+- **mma-tier3-worker:** Focused on TDD implementation, surgical code changes, and following specific specs.
+- **mma-tier4-qa:** Focused on test analysis, error summarization, and bug reproduction.
+
+### 2. Specialized CLI: `mma-exec`
+A new Python-based CLI tool to replace/extend `run_subagent.ps1`:
+- **Role Scoping:** Automatically determines which project documents (Product, Tech Stack, etc.) to include based on the active role.
+- **AST Skeleton Views:** Integrates with `tree-sitter` to generate and provide only the interface/signature skeletons of dependency files to Tier 3 Workers.
+- **Context Amnesia Protocol:** Ensures each role execution starts with a fresh, scoped context to prevent history-induced hallucinations.
+- **Conductor Integration:** Designed to be called by the Conductor agent or manually by the developer.
+
+### 3. Workflow Integration
+- Update `conductor/workflow.md` to formalize the use of `mma-exec` and the tiered skills.
+- Add specific commands/aliases within the Conductor context to trigger role hand-offs.
+
+## Non-Functional Requirements
+- **Performance:** Context gathering (including AST parsing) must be fast enough for interactive use.
+- **Transparency:** All hand-offs and context inclusions must be logged for developer auditing.
+
+## Acceptance Criteria
+- [ ] Four new skills are registered and accessible.
+- [ ] `mma-exec` tool can successfully spawn a worker with only AST skeleton views of requested dependencies.
+- [ ] A test task can be implemented using the tiered delegation flow without manual context curation.
+- [ ] `workflow.md` documentation is fully updated.
+
+## Out of Scope
+- Migrating existing tracks to the new architecture (only new tasks/tracks are required to use it).
+- Automating the *decision* of when to hand off (remains semi-automated/manual per user preference).

gemini_cli_adapter.py

@@ -2,6 +2,7 @@ import subprocess
 import json
 import sys
 import time
+import os
 
 class GeminiCliAdapter:
     def __init__(self, binary_path="gemini"):
@@ -24,13 +25,17 @@ class GeminiCliAdapter:
 
         accumulated_text = ""
         
+        env = os.environ.copy()
+        env["GEMINI_CLI_HOOK_CONTEXT"] = "manual_slop"
+
         process = subprocess.Popen(
             command,
             stdin=subprocess.PIPE,
             stdout=subprocess.PIPE,
             stderr=subprocess.PIPE,
             text=True,
-            shell=True
+            shell=True,
+            env=env
         )
 
         try:

scripts/cli_tool_bridge.py

@@ -29,7 +29,17 @@ def main():
         tool_name = hook_input.get('tool_name')
         tool_args = hook_input.get('tool_input', {})
 
-        # 3. Use 'ApiHookClient' (assuming GUI is on http://127.0.0.1:8999)
+        # 3. Check context — if not running via Manual Slop, we pass through (allow)
+        # This prevents the hook from affecting normal CLI usage.
+        hook_context = os.environ.get("GEMINI_CLI_HOOK_CONTEXT")
+        if hook_context != "manual_slop":
+             print(json.dumps({
+                "decision": "allow", 
+                "reason": "Non-programmatic usage (GEMINI_CLI_HOOK_CONTEXT not set)."
+            }))
+             return
+
+        # 4. Use 'ApiHookClient' (assuming GUI is on http://127.0.0.1:8999)
         client = ApiHookClient(base_url="http://127.0.0.1:8999")
         
         try:
@@ -38,20 +48,22 @@ def main():
             response = client.request_confirmation(tool_name, tool_args)
 
             if response and response.get('approved') is True:
-                # 5. Print 'allow' decision
+                # 6. Print 'allow' decision
                 print(json.dumps({"decision": "allow"}))
             else:
-                # 6. Print 'deny' decision
+                # 7. Print 'deny' decision
                 print(json.dumps({
                     "decision": "deny", 
-                    "reason": "User rejected tool execution."
+                    "reason": "User rejected tool execution in GUI."
                 }))
 
         except Exception as e:
-            # 7. Handle cases where hook server is not reachable
+            # 8. Handle cases where hook server is not reachable
+            # If we ARE in manual_slop context but can't reach the server, we should DENY
+            # because the user expects to be in control.
             print(json.dumps({
                 "decision": "deny", 
-                "reason": f"Hook server unreachable or error occurred: {str(e)}"
+                "reason": f"Manual Slop hook server unreachable: {str(e)}"
             }))
 
     except Exception as e: