From 95381c258c712423eb1a37da6405ab3c38160514 Mon Sep 17 00:00:00 2001
From: Ed_ <edwardgz@gmail.com>
Date: Mon, 9 Mar 2026 22:35:52 -0400
Subject: [PATCH] chore(conductor): Mark track 'Saved System Prompt Presets' as
 complete

---
 conductor/tracks.md                           |    2 +-
 .../tracks/saved_presets_20260308/plan.md     |   28 +-
 config.toml                                   |    9 +-
 manualslop_layout.ini                         |  134 +-
 mock_debug_prompt.txt                         | 1486 +++++++++++++++++
 src/app_controller.py                         |   85 +-
 src/gui_2.py                                  |   32 +-
 src/presets.py                                |   38 +-
 tests/test_saved_presets_sim.py               |   73 +-
 9 files changed, 1729 insertions(+), 158 deletions(-)

diff --git a/conductor/tracks.md b/conductor/tracks.md
index 2f13d30..2f29c58 100644
--- a/conductor/tracks.md
+++ b/conductor/tracks.md
@@ -85,7 +85,7 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 ### Manual UX Controls
 
-1. [~] **Track: Saved System Prompt Presets**
+1. [x] **Track: Saved System Prompt Presets**
    *Link: [./tracks/saved_presets_20260308/](./tracks/saved_presets_20260308/)*
    *Goal: Ability to have saved presets for global and project system prompts. Includes full AI profiles with temperature and top_p settings, managed via a dedicated GUI modal.*
 
diff --git a/conductor/tracks/saved_presets_20260308/plan.md b/conductor/tracks/saved_presets_20260308/plan.md
index 5d35c57..36b3101 100644
--- a/conductor/tracks/saved_presets_20260308/plan.md
+++ b/conductor/tracks/saved_presets_20260308/plan.md
@@ -28,19 +28,19 @@
 - [x] Task: Conductor - User Manual Verification 'Phase 2: UI: Settings Integration' (Protocol in workflow.md)
 
 ## Phase 3: UI: Preset Manager Modal
-- [~] Task: Create the `PresetManagerModal` in `gui_2.py` (or a separate module).
-    - [ ] Implement a list view of all presets (global and project).
-    - [ ] Implement "Add", "Edit", and "Delete" functionality.
-    - [ ] Ensure validation for unique names.
-- [ ] Task: Add a button to open the manager modal from the settings panels.
-- [ ] Task: Write integration tests for the Preset Manager using `live_gui`.
-    - [ ] Verify creating a new preset adds it to the list and dropdown.
-    - [ ] Verify editing an existing preset updates it correctly.
-    - [ ] Verify deleting a preset removes it from the list and dropdown.
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: UI: Preset Manager Modal' (Protocol in workflow.md)
+- [x] Task: Create the `PresetManagerModal` in `gui_2.py` (or a separate module).
+    - [x] Implement a list view of all presets (global and project).
+    - [x] Implement "Add", "Edit", and "Delete" functionality.
+    - [x] Ensure validation for unique names.
+- [x] Task: Add a button to open the manager modal from the settings panels.
+- [x] Task: Write integration tests for the Preset Manager using `live_gui`.
+    - [x] Verify creating a new preset adds it to the list and dropdown.
+    - [x] Verify editing an existing preset updates it correctly.
+    - [x] Verify deleting a preset removes it from the list and dropdown.
+- [x] Task: Conductor - User Manual Verification 'Phase 3: UI: Preset Manager Modal' (Protocol in workflow.md)
 
 ## Phase 4: Final Integration & Polish
-- [ ] Task: Ensure robust error handling for missing or malformed `.toml` files.
-- [ ] Task: Final UI polish (spacing, icons, tooltips).
-- [ ] Task: Run full suite of relevant tests.
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Final Integration & Polish' (Protocol in workflow.md)
+- [x] Task: Ensure robust error handling for missing or malformed `.toml` files.
+- [x] Task: Final UI polish (spacing, icons, tooltips).
+- [x] Task: Run full suite of relevant tests.
+- [x] Task: Conductor - User Manual Verification 'Phase 4: Final Integration & Polish' (Protocol in workflow.md)
diff --git a/config.toml b/config.toml
index 92d9bf2..e5da747 100644
--- a/config.toml
+++ b/config.toml
@@ -22,6 +22,7 @@ separate_message_panel = false
 separate_response_panel = false
 separate_tool_calls_panel = false
 bg_shader_enabled = true
+crt_filter_enabled = false
 
 [gui.show_windows]
 "Context Hub" = true
@@ -39,15 +40,15 @@ Response = false
 "Tool Calls" = false
 Theme = true
 "Log Management" = true
-Diagnostics = false
+Diagnostics = true
 
 [theme]
 palette = "Nord Dark"
 font_path = "C:/projects/manual_slop/assets/fonts/Inter-Regular.ttf"
 font_size = 12.0
-scale = 1.25
-transparency = 0.6499999761581421
-child_transparency = 0.7200000286102295
+scale = 1.2999999523162842
+transparency = 0.550000011920929
+child_transparency = 0.6399999856948853
 
 [mma]
 max_workers = 4
diff --git a/manualslop_layout.ini b/manualslop_layout.ini
index 2830f47..a603074 100644
--- a/manualslop_layout.ini
+++ b/manualslop_layout.ini
@@ -44,12 +44,12 @@ Collapsed=0
 DockId=0x00000001,0
 
 [Window][Message]
-Pos=1005,726
+Pos=1890,1100
 Size=1065,548
 Collapsed=0
 
 [Window][Response]
-Pos=1009,1217
+Pos=2086,1780
 Size=1036,351
 Collapsed=0
 
@@ -73,8 +73,8 @@ Collapsed=0
 DockId=0xAFC85805,2
 
 [Window][Theme]
-Pos=0,26
-Size=848,827
+Pos=0,30
+Size=762,943
 Collapsed=0
 DockId=0x00000005,1
 
@@ -84,14 +84,14 @@ Size=900,700
 Collapsed=0
 
 [Window][Diagnostics]
-Pos=2622,27
-Size=1218,2110
+Pos=2674,26
+Size=1166,1678
 Collapsed=0
-DockId=0x00000004,1
+DockId=0x0000000C,2
 
 [Window][Context Hub]
-Pos=0,26
-Size=848,827
+Pos=0,30
+Size=762,943
 Collapsed=0
 DockId=0x00000005,0
 
@@ -102,26 +102,26 @@ Collapsed=0
 DockId=0x0000000D,0
 
 [Window][Discussion Hub]
-Pos=1736,26
-Size=884,1463
+Pos=1668,30
+Size=1004,2107
 Collapsed=0
 DockId=0x00000013,0
 
 [Window][Operations Hub]
-Pos=850,26
-Size=884,1463
+Pos=764,30
+Size=902,2107
 Collapsed=0
 DockId=0x00000012,0
 
 [Window][Files & Media]
-Pos=0,1885
-Size=848,252
+Pos=0,1849
+Size=762,288
 Collapsed=0
 DockId=0x00000002,0
 
 [Window][AI Settings]
-Pos=0,855
-Size=848,1028
+Pos=0,975
+Size=762,872
 Collapsed=0
 DockId=0x00000001,0
 
@@ -131,16 +131,16 @@ Size=416,325
 Collapsed=0
 
 [Window][MMA Dashboard]
-Pos=2622,26
-Size=1218,2111
+Pos=2674,30
+Size=1166,1675
 Collapsed=0
-DockId=0x00000004,1
+DockId=0x0000000C,0
 
 [Window][Log Management]
-Pos=2622,26
-Size=1218,2111
+Pos=2674,30
+Size=1166,1675
 Collapsed=0
-DockId=0x00000004,0
+DockId=0x0000000C,1
 
 [Window][Track Proposal]
 Pos=709,326
@@ -148,28 +148,28 @@ Size=262,209
 Collapsed=0
 
 [Window][Tier 1: Strategy]
-Pos=850,1491
-Size=306,646
+Pos=2674,1707
+Size=1166,430
 Collapsed=0
-DockId=0x00000014,0
+DockId=0x0000000F,0
 
 [Window][Tier 2: Tech Lead]
-Pos=1158,1491
-Size=550,646
+Pos=2674,1707
+Size=1166,430
 Collapsed=0
-DockId=0x00000016,0
+DockId=0x0000000F,1
 
 [Window][Tier 4: QA]
-Pos=2215,1491
-Size=405,646
+Pos=2674,1707
+Size=1166,430
 Collapsed=0
-DockId=0x00000019,0
+DockId=0x0000000F,2
 
 [Window][Tier 3: Workers]
-Pos=1710,1491
-Size=503,646
+Pos=764,30
+Size=902,2107
 Collapsed=0
-DockId=0x00000018,0
+DockId=0x00000012,1
 
 [Window][Approve PowerShell Command]
 Pos=649,435
@@ -352,11 +352,11 @@ Column 3  Width=20
 Column 4  Weight=1.0000
 
 [Table][0x2A6000B6,4]
-RefScale=14
-Column 0  Width=42
-Column 1  Width=64
+RefScale=18
+Column 0  Width=54
+Column 1  Width=82
 Column 2  Weight=1.0000
-Column 3  Width=107
+Column 3  Width=137
 
 [Table][0x8BCC69C7,6]
 RefScale=13
@@ -375,11 +375,11 @@ Column 2  Weight=1.0000
 Column 3  Width=106
 
 [Table][0x2C515046,4]
-RefScale=14
-Column 0  Width=61
+RefScale=18
+Column 0  Width=58
 Column 1  Weight=1.0000
-Column 2  Width=161
-Column 3  Width=42
+Column 2  Width=138
+Column 3  Width=54
 
 [Table][0xD99F45C5,4]
 Column 0  Sort=0v
@@ -400,36 +400,30 @@ Column 1  Width=100
 Column 2  Weight=1.0000
 
 [Table][0xA02D8C87,3]
-RefScale=14
-Column 0  Width=160
-Column 1  Width=106
+RefScale=16
+Column 0  Width=182
+Column 1  Width=120
 Column 2  Weight=1.0000
 
 [Docking][Data]
-DockNode                ID=0x00000008 Pos=3125,170 Size=593,1157 Split=Y
-  DockNode              ID=0x00000009 Parent=0x00000008 SizeRef=1029,147 Selected=0x0469CA7A
-  DockNode              ID=0x0000000A Parent=0x00000008 SizeRef=1029,145 Selected=0xDF822E02
-DockSpace               ID=0xAFC85805 Window=0x079D3A04 Pos=0,26 Size=3840,2111 Split=X
-  DockNode              ID=0x00000003 Parent=0xAFC85805 SizeRef=2620,1183 Split=X
-    DockNode            ID=0x0000000B Parent=0x00000003 SizeRef=404,1186 Split=X Selected=0xF4139CA2
-      DockNode          ID=0x00000007 Parent=0x0000000B SizeRef=848,858 Split=Y Selected=0x8CA2375C
-        DockNode        ID=0x00000005 Parent=0x00000007 SizeRef=295,827 Selected=0x8CA2375C
-        DockNode        ID=0x00000006 Parent=0x00000007 SizeRef=295,1286 Split=Y Selected=0x7BD57D6A
-          DockNode      ID=0x00000001 Parent=0x00000006 SizeRef=824,1032 CentralNode=1 Selected=0x7BD57D6A
-          DockNode      ID=0x00000002 Parent=0x00000006 SizeRef=824,252 Selected=0x1DCB2623
-      DockNode          ID=0x0000000E Parent=0x0000000B SizeRef=1770,858 Split=Y Selected=0x418C7449
-        DockNode        ID=0x00000010 Parent=0x0000000E SizeRef=868,1466 Split=X Selected=0x418C7449
-          DockNode      ID=0x00000012 Parent=0x00000010 SizeRef=884,402 Selected=0x418C7449
-          DockNode      ID=0x00000013 Parent=0x00000010 SizeRef=884,402 Selected=0x6F2B5B04
-        DockNode        ID=0x00000011 Parent=0x0000000E SizeRef=868,647 Split=X Selected=0x5CDB7A4B
-          DockNode      ID=0x00000014 Parent=0x00000011 SizeRef=306,837 Selected=0xBB346584
-          DockNode      ID=0x00000015 Parent=0x00000011 SizeRef=1462,837 Split=X Selected=0x5CDB7A4B
-            DockNode    ID=0x00000016 Parent=0x00000015 SizeRef=550,837 Selected=0x390E7942
-            DockNode    ID=0x00000017 Parent=0x00000015 SizeRef=910,837 Split=X Selected=0x655BC6E9
-              DockNode  ID=0x00000018 Parent=0x00000017 SizeRef=503,874 Selected=0x655BC6E9
-              DockNode  ID=0x00000019 Parent=0x00000017 SizeRef=405,874 Selected=0x5CDB7A4B
-    DockNode            ID=0x0000000D Parent=0x00000003 SizeRef=435,1186 Selected=0x363E93D6
-  DockNode              ID=0x00000004 Parent=0xAFC85805 SizeRef=1218,1183 Selected=0x2C0206CE
+DockNode            ID=0x00000008 Pos=3125,170 Size=593,1157 Split=Y
+  DockNode          ID=0x00000009 Parent=0x00000008 SizeRef=1029,147 Selected=0x0469CA7A
+  DockNode          ID=0x0000000A Parent=0x00000008 SizeRef=1029,145 Selected=0xDF822E02
+DockSpace           ID=0xAFC85805 Window=0x079D3A04 Pos=0,30 Size=3840,2107 Split=X
+  DockNode          ID=0x00000003 Parent=0xAFC85805 SizeRef=2672,1183 Split=X
+    DockNode        ID=0x0000000B Parent=0x00000003 SizeRef=404,1186 Split=X Selected=0xF4139CA2
+      DockNode      ID=0x00000007 Parent=0x0000000B SizeRef=762,858 Split=Y Selected=0x8CA2375C
+        DockNode    ID=0x00000005 Parent=0x00000007 SizeRef=295,943 Selected=0xF4139CA2
+        DockNode    ID=0x00000006 Parent=0x00000007 SizeRef=295,1168 Split=Y Selected=0x7BD57D6A
+          DockNode  ID=0x00000001 Parent=0x00000006 SizeRef=824,872 CentralNode=1 Selected=0x7BD57D6A
+          DockNode  ID=0x00000002 Parent=0x00000006 SizeRef=824,288 Selected=0x1DCB2623
+      DockNode      ID=0x0000000E Parent=0x0000000B SizeRef=1908,858 Split=X Selected=0x418C7449
+        DockNode    ID=0x00000012 Parent=0x0000000E SizeRef=902,402 Selected=0x418C7449
+        DockNode    ID=0x00000013 Parent=0x0000000E SizeRef=1004,402 Selected=0x6F2B5B04
+    DockNode        ID=0x0000000D Parent=0x00000003 SizeRef=435,1186 Selected=0x363E93D6
+  DockNode          ID=0x00000004 Parent=0xAFC85805 SizeRef=1166,1183 Split=Y Selected=0x3AEC3498
+    DockNode        ID=0x0000000C Parent=0x00000004 SizeRef=1074,1679 Selected=0x2C0206CE
+    DockNode        ID=0x0000000F Parent=0x00000004 SizeRef=1074,431 Selected=0x5CDB7A4B
 
 ;;;<<<Layout_655921752_Default>>>;;;
 ;;;<<<HelloImGui_Misc>>>;;;
diff --git a/mock_debug_prompt.txt b/mock_debug_prompt.txt
index 2ec238e..72e15cd 100644
--- a/mock_debug_prompt.txt
+++ b/mock_debug_prompt.txt
@@ -861,3 +861,1489 @@ PROMPT:
 role: tool
 Here are the results: {"content": "done"}
 ------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+PATH: Epic Initialization — please produce tracks
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please generate the implementation tickets for this track.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please read test.txt
+You are assigned to Ticket T1.
+Task Description: do something
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+role: tool
+Here are the results: {"content": "done"}
+------------------
+--- MOCK INVOKED ---
+ARGS: ['C:\\projects\\manual_slop\\tests\\mock_gemini_cli.py', '-m', 'gemini-2.5-flash-lite', '--prompt', '', '--output-format', 'stream-json']
+PROMPT:
+You are a helpful coding assistant with access to a PowerShell tool (run_powershell) and MCP tools (file access: read_file, list_directory, search_files, get_file_summary, web access: web_search, fetch_url). When calling file/directory tools, always use the 'path' parameter for the target path. When asked to create or edit files, prefer targeted edits over full rewrites. Always explain what you are doing before invoking the tool.
+
+When writing or rewriting large files (especially those containing quotes, backticks, or special characters), avoid python -c with inline strings. Instead: (1) write a .py helper script to disk using a PS here-string (@'...'@ for literal content), (2) run it with `python <script>`, (3) delete the helper. For small targeted edits, use PowerShell's (Get-Content) / .Replace() / Set-Content or Add-Content directly.
+
+When making function calls using tools that accept array or object parameters ensure those are structured using JSON. For example:
+When you need to verify a change, rely on the exit code and stdout/stderr from the tool — the user's context files are automatically refreshed after every tool call, so you do NOT need to re-read files that are already provided in the <context> block.
+
+[USER SYSTEM PROMPT]
+
+You are the Tier 1 Orchestrator (Product Manager) for the Manual Slop project.
+Your role is high-level strategic planning, architecture enforcement, and cross-module delegation.
+You operate strictly on metadata, summaries, and executive-level directives.
+NEVER request or attempt to read raw implementation code unless specifically provided in a Macro-Diff.
+Maintain a "Godot ECS Flat List format" (JSON array of objects) for structural outputs.
+
+PATH: Epic Initialization (Project Planning)
+GOAL: Break down a massive feature request into discrete Implementation Tracks.
+
+CONSTRAINTS:
+- IGNORE all source code, AST skeletons, and previous micro-task histories.
+- FOCUS ONLY on the Repository Map and Project Meta-State.
+
+OUTPUT REQUIREMENT:
+Return a JSON array of 'Tracks'. Each track object must follow the Godot ECS Flat List format:
+[
+  {
+    "id": "track_unique_id",
+    "type": "Track",
+    "module": "target_module_name",
+    "persona": "required_tech_lead_persona",
+    "severity": "Low|Medium|High",
+    "goal": "Descriptive goal",
+    "acceptance_criteria": ["criteria_1", "criteria_2"]
+  },
+  ...
+]
+
+
+<context>
+
+</context>
+
+### USER REQUEST:
+Add timestamps
+
+### REPOSITORY MAP:
+
+
+### TRACK HISTORY:
+Track: api_hooks_verification_20260223
+Status: new
+Overview: This track focuses on integrating the existing, previously implemented API hooks (from track `test_hooks_20260223`) into the Conductor workflow. The primary goal is to automate the verification steps within the "Phase Completion Verification and Checkpointing Protocol", reducing the need for manual user intervention and enabling a more streamlined, automated development process.
+---
+Track: api_metrics_20260223
+Status: new
+Overview: This track aims to optimize token efficiency and transparency by reviewing and improving how vendor APIs (Gemini and Anthropic) handle conservative context pruning. The primary focus is on extracting, plotting, and exposing deep metrics to the GUI so developers can intuit how close they are to API limits (e.g., token caps, cache counts, history bleed).
+---
+Track: api_vendor_alignment_20260223
+Status: new
+Overview: This track involves a comprehensive audit of the "Manual Slop" codebase to ensure that the integration with Google Gemini (`google-genai`) and Anthropic Claude (`anthropic`) SDKs aligns perfectly with their latest official documentation and best practices. The goal is to identify discrepancies, performance bottlenecks, or deprecated patterns and implement the necessary fixes.
+---
+Track: architecture_boundary_hardening_20260302
+Status: new
+Overview: The `manual_slop` project sandbox provides AI meta-tooling (`mma_exec.py`, `tool_call.py`) to orchestrate its own development. When AI agents added advanced AST tools (like `set_file_slice`) to `mcp_client.py` for meta-tooling, they failed to fully integrate them into the application's GUI, config, or HITL (Human-In-The-Loop) safety models. Additionally, meta-tooling scripts are bleeding tokens and rely on non-portable hardcoded machine paths, while the internal application's state machine can deadlock.
+---
+Track: cache_analytics_20260306
+Status: planned
+Overview: Gemini cache hit/miss visualization, memory usage, TTL status display. Uses existing `ai_client.get_gemini_cache_stats()` which is implemented but has no GUI representation.
+---
+Track: codebase_migration_20260302
+Status: new
+Overview: This track focuses on restructuring the codebase to alleviate clutter by moving the main implementation files from the project root into a dedicated `src/` directory. Additionally, files that are completely unused by the current implementation will be automatically identified and removed. A new clean entry point (`sloppy.py`) will be created in the root directory.
+---
+Track: comprehensive_gui_ux_20260228
+Status: completed
+Overview: This track enhances the existing MMA orchestration GUI from its current functional-but-minimal state to a production-quality control surface. The existing implementation already has a working Track Browser, DAG tree visualizer, epic planning flow, approval dialogs, and token usage table. This track focuses on the **gaps**: dedicated tier stream panels, DAG editing, track-scoped discussions, conductor lifecycle GUI forms, cost tracking, and visual polish.
+---
+Track: conductor_workflow_improvements_20260302
+Status: new
+Overview: Recent Tier 2 track implementations have resulted in feature bleed, redundant code, unread state variables, and degradation of TDD discipline (e.g., zero-assertion tests).
+This track updates the Conductor documentation (`workflow.md`) and the Gemini skills for Tiers 2 and 3 to hard-enforce TDD, prevent hallucinated "mock" implementations, and enforce strict codebase auditing before writing code.
+---
+Track: consolidate_cruft_and_log_taxonomy_20260228
+Status: unknown
+Overview: This track focuses on cleaning up the project root by consolidating temporary and test-related files into a dedicated directory and establishing a structured taxonomy for session logs. This will improve project organization and make manual file exploration easier before a dedicated GUI log viewer is implemented.
+---
+Track: context_management_20260223
+Status: new
+Overview: This track implements UI improvements and structural changes to Manual Slop to provide explicit visualization of context memory usage and token consumption, fulfilling the "Expert systems level utility" and "Full control" product goals.
+---
+Track: context_token_viz_20260301
+Status: new
+Overview: product.md lists "Context & Memory Management" as primary use case #2: "Better visualization and management of token usage and context memory, allowing developers to optimize prompt limits manually." The backend already computes everything needed via `ai_client.get_history_bleed_stats()` (ai_client.py:1657-1796, 140 lines). This track builds the UI to expose it.
+---
+Track: cost_token_analytics_20260306
+Status: planned
+Overview: # Implementation Plan: Cost & Token Analytics Panel (cost_token_analytics_20260306)
+
+> **Reference:** [Spec](./spec.md) | [Architecture Guide](../../../docs/guide_architecture.md)
+
+## Phase 1: Foundat...
+---
+Track: deepseek_support_20260225
+Status: new
+Overview: Implement a new AI provider module to support the DeepSeek API within the Manual Slop application. This integration will leverage a dedicated SDK to provide access to high-performance models (DeepSeek-V3 and DeepSeek-R1) with support for streaming, tool calling, and detailed reasoning traces.
+---
+Track: deep_ast_context_pruning_20260306
+Status: planned
+Overview: Use tree_sitter to parse target file AST and inject condensed skeletons into worker prompts. Currently workers receive full file context; this track reduces token burn by injecting only relevant function/method signatures.
+---
+Track: documentation_refresh_20260224
+Status: new
+Overview: This track implements a high-density, expert-level documentation suite for the Manual Slop project. The documentation style is strictly modeled after the **pedagogical and narrative standards** of `gencpp` and `VEFontCache-Odin`. It moves beyond simple "User Guides" to provide a **"USA Graphics Company"** architectural reference: high information density, tactical technical transparency, and a narrative intent that guides a developer from high-level philosophy to low-level implementation.
+---
+Track: enhanced_context_control_20260307
+Status: planned
+Overview: Give developers granular control over how files are included in the AI context and provide visibility into the active Gemini cache state. This involves moving away from a simple list of files to a structured format with per-file flags (`auto_aggregate`, `force_full`), revamping the UI to display this state, and updating the context builders and API clients to respect and expose these details.
+---
+Track: event_driven_metrics_20260223
+Status: new
+Overview: Refactor the API metrics update mechanism to be event-driven. Currently, the UI likely polls or recalculates metrics on every frame. This track will implement a signal/event system where `ai_client.py` broadcasts updates only when significant API activities (requests, responses, tool calls, or stream chunks) occur.
+---
+Track: feature_bleed_cleanup_20260302
+Status: new
+Overview: Multiple tracks added code to `gui_2.py` without removing the old versions, leaving
+dead duplicate methods, conflicting menu bar designs, and redundant state initializations.
+This track removes confirmed dead code, resolves the two-menubar conflict, and cleans
+up the token budget layout regression — restoring a consistent, non-contradictory design state.
+---
+Track: gemini_cli_headless_20260224
+Status: new
+Overview: This track integrates the `gemini` CLI as a headless backend provider for Manual Slop. This allows users to leverage their Gemini subscription and the CLI's advanced features (e.g., specialized sub-agents like `codebase_investigator`, structured JSON streaming, and robust session management) directly within the Manual Slop GUI.
+---
+Track: gemini_cli_parity_20260225
+Status: new
+Overview: Achieve full functional and behavioral parity between the Gemini CLI integration (`gemini_cli_adapter.py`, `cli_tool_bridge.py`) and the direct Gemini API implementation (`ai_client.py`). This ensures that users leveraging the Gemini CLI as a headless backend provider experience the same level of capability, reliability, and observability as direct API users.
+---
+Track: gui2_feature_parity_20260223
+Status: new
+Overview: # Specification: GUIv2 Feature Parity
+
+## 1. Overview
+
+This track aims to bring `gui_2.py` (the `imgui-bundle` based UI) to feature parity with the existing `gui.py` (the `dearpygui` based UI). This i...
+---
+Track: gui2_parity_20260224
+Status: new
+Overview: The project is transitioning from `gui.py` (Dear PyGui-based) to `gui_2.py` (ImGui Bundle-based) to leverage advanced multi-viewport and docking features not natively supported by Dear PyGui. This track focuses on achieving full visual, functional, and performance parity between the two implementations, ultimately enabling the decommissioning of the original `gui.py`.
+---
+Track: gui_decoupling_controller_20260302
+Status: new
+Overview: `gui_2.py` currently operates as a Monolithic God Object (3,500+ lines). It violates the Data-Oriented Design heuristic by owning complex business logic, orchestrator hooks, and markdown file building. This track extracts the core state machine and lifecycle into a headless `app_controller.py`, turning the GUI into a pure immediate-mode view.
+---
+Track: gui_layout_refinement_20260223
+Status: new
+Overview: This track focuses on a holistic review and reorganization of the Manual Slop GUI. The goal is to ensure that AI tunings, diagnostic features, context management, and discussion history are logically placed to support an expert-level "Multi-Viewport" workflow. We will strengthen the "Arcade Aesthetics" and "Tactile Density" values while ensuring the layout remains intuitive for power users.
+---
+Track: gui_performance_20260223
+Status: new
+Overview: This track focuses on identifying and resolving severe frametime performance issues in the Manual Slop GUI. Current observations indicate massive frametime bloat even on idle startup, with performance significantly regressing (target 60 FPS / <16.6ms) since commit `8aa70e287fbf93e669276f9757965d5a56e89b10`.
+---
+Track: gui_performance_profiling_20260307
+Status: unknown
+Overview: Implement fine-grained performance profiling within the main ImGui rendering loop (`gui_2.py`) to ensure adherence to data-oriented and immediate mode heuristics. This track will provide visual diagnostics for high-overhead UI components, allowing developers to monitor and optimize render frame times.
+---
+Track: gui_sim_extension_20260224
+Status: new
+Overview: This track aims to expand the test simulation suite by introducing comprehensive, in-breadth tests that cover all facets of the GUI interaction. The original small test simulation will be preserved as a useful baseline. The new extended tests will be structured as multiple focused, modular scripts rather than a single long-running journey, ensuring maintainability and targeted coverage.
+---
+Track: history_segregation_20260224
+Status: new
+Overview: Currently, `manual_slop.toml` stores both project configuration and the entire discussion history. This leads to redundancy and potential context bloat if the AI agent reads the raw TOML file via its tools. This track will move the discussion history to a dedicated sibling TOML file (`history.toml`) and strictly blacklist it from the AI agent's file tools to ensure it only interacts with the curated context provided in the prompt.
+---
+Track: kill_abort_workers_20260306
+Status: planned
+Overview: Add ability to kill/abort a running Tier 3 worker mid-execution. Currently workers run to completion; add cancel button with forced termination option.
+---
+Track: live_gui_testing_20260223
+Status: new
+Overview: Update the testing suite to ensure all tests (especially GUI-related and integration tests) communicate with a live running instance of `gui.py` started with the `--enable-test-hooks` argument. This ensures that tests can verify the actual application state and metrics via the built-in API hooks.
+---
+Track: live_ux_test_20260223
+Status: new
+Overview: This track implements a robust, "human-like" interaction test suite for Manual Slop. The suite will simulate a real user's workflow—from project creation to complex AI discussions and history management—using the application's API hooks. It aims to verify the "Integrated Workspace" functionality, tool execution, and history persistence without requiring manual human input, while remaining slow enough for visual audit.
+---
+Track: logging_refactor_20260226
+Status: new
+Overview: Currently, `gui_2.py` and the test suites generate a large number of log files in a flat `logs/` directory. These logs accumulate quickly, especially during incremental development and testing. This track aims to organize logs into session-based sub-directories and implement a heuristic-based pruning system to keep the log directory clean while preserving valuable sessions.
+---
+Track: manual_block_control_20260306
+Status: planned
+Overview: Allow user to manually block or unblock tickets with custom reasons. Currently blocked tickets rely solely on dependency resolution; add manual override capability.
+---
+Track: manual_skeleton_injection_20260306
+Status: planned
+Overview: Add UI controls to manually inject file skeletons into discussions. Allow user to preview skeleton content before sending to AI, with option to toggle between skeleton and full file.
+---
+Track: manual_slop_headless_20260225
+Status: new
+Overview: Transform Manual Slop into a decoupled, container-friendly backend service. This track enables the core AI orchestration and tool execution logic to run without a GUI, exposing its capabilities via a secured REST API optimized for an Unraid Docker environment.
+---
+Track: minimax_provider_20260306
+Status: unknown
+Overview: Add MiniMax as a new AI provider to Manual Slop. MiniMax provides high-performance text generation models (M2.5, M2.1, M2) with massive context windows (200k+ tokens) and competitive pricing.
+---
+Track: mma_agent_focus_ux_20260302
+Status: new
+Overview: All MMA observability panels (comms history, tool calls, discussion) display
+global/session-scoped data. When 4 tiers are running concurrently, their traffic
+is indistinguishable. This track adds a `source_tier` field to every comms and
+tool log entry at the point of emission, then adds a "Focus Agent" selector that
+filters the Operations Hub panels to show only one tier's traffic at a time.
+
+**Depends on:** `feature_bleed_cleanup_20260302` (Phase 1 removes the dead comms
+panel duplicate; this track extends the live panel at gui_2.py:~3400).
+---
+Track: MMA Core Engine Implementation
+Status: planning
+Overview: # Specification: MMA Core Engine Implementation
+
+## 1. Overview
+This track consolidates the implementation of the 4-Tier Hierarchical Multi-Model Architecture into the `manual_slop` codebase. The arch...
+---
+Track: MMA Dashboard Visualization Overhaul
+Status: planned
+Overview: Make the invisible backend operations visible and interactive. The current GUI is too barebones to effectively manage a multi-agent system. This track overhauls the MMA Dashboard to provide real-time insights into tracks, task dependencies, and agent streams.
+---
+Track: MMA Data Architecture & DAG Engine
+Status: planned
+Overview: Restructure how `manual_slop` stores and executes work. The current implementation relies on global state and linear execution, which does not support the complexity of multi-agent, task-based workflows. This track establishes a robust, data-oriented foundation using track-scoped state and a native Python Directed Acyclic Graph (DAG) engine.
+---
+Track: mma_formalization_20260225
+Status: new
+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.
+---
+Track: mma_implementation_20260224
+Status: new
+Overview: # Specification: 4-Tier Architecture Implementation & Conductor Self-Improvement
+
+## 1. Overview
+This track encompasses two major phases. Phase 1 focuses on designing a comprehensive, step-by-step imp...
+---
+Track: mma_multiworker_viz_20260306
+Status: planned
+Overview: Split-view GUI for parallel worker streams per tier. Visualize multiple concurrent workers with individual status, output tabs, and resource usage. Enable kill/restart per worker.
+---
+Track: MMA Orchestrator Integration
+Status: in-progress
+Overview: Implement the full hierarchical orchestration loop, connecting Tier 1 (PM) strategic planning with Tier 2 (Tech Lead) tactical ticket generation. This track will enable the GUI to autonomously break down high-level user 'Epics' into actionable tracks and tickets, and manage their execution through the multi-agent system.
+---
+Track: mma_pipeline_fix_20260301
+Status: new
+Overview: The MMA pipeline has a verified code path from `run_worker_lifecycle` → `_queue_put("response", ...)` → `_process_event_queue` → `_pending_gui_tasks("handle_ai_response")` → `mma_streams[stream_id] = text`. However, the robust_live_simulation track's session compression (2026-02-28) documented that Tier 3 worker output never appears in `mma_streams` during actual GUI operation. The simulation only ever sees `'Tier 1'` in `mma_streams` keys.
+
+This track diagnoses and fixes the pipeline break, then verifies end-to-end that worker output flows from `ai_client.send()` through to the GUI's `mma_streams` dict.
+---
+Track: mma_utilization_refinement_20260226
+Status: new
+Overview: Refine the Multi-Model Architecture (MMA) implementation within the Conductor framework to ensure clear role segregation, proper tool permissions, and improved observability for sub-agents.
+---
+Track: mma_verification_20260225
+Status: new
+Overview: This track aims to review and verify the implementation of the 4-Tier Hierarchical Multi-Model Architecture (MMA) within the Conductor framework. It will confirm that Conductor operates as a Tier 2 Tech Lead/Orchestrator and can successfully delegate tasks to Tier 3 (Workers) and Tier 4 (QA/Utility) sub-agents. A key part of this track is investigating whether this hierarchy should be enforced via a single centralized skill or through separate role-based sub-agent definitions.
+---
+Track: mma_verification_mock
+Status: new
+Overview: This is a mock track designed to verify the full Tier 2 -> Tier 3 -> Tier 4 delegation flow within the Conductor framework.
+---
+Track: native_orchestrator_20260306
+Status: planned
+Overview: Absorb `mma_exec.py` functionality into core application. Manual Slop natively reads/writes plan.md, manages metadata.json, and orchestrates MMA tiers in pure Python without external CLI subprocess calls.
+---
+Track: on_demand_def_lookup_20260306
+Status: planned
+Overview: Add ability for agent to request specific class/function definitions during discussion. Parse @symbol syntax to trigger lookup and display inline in the discussion.
+---
+Track: per_ticket_model_20260306
+Status: planned
+Overview: Allow user to manually select which model to use for a specific ticket, overriding the default tier model. Useful for forcing smarter model on hard tickets.
+---
+Track: pipeline_pause_resume_20260306
+Status: planned
+Overview: Add global pause/resume for entire DAG execution pipeline. Allow user to freeze all worker activity and resume later without losing state.
+---
+Track: python_style_refactor_20260227
+Status: unknown
+Overview: # Specification: AI-Optimized Python Style Refactor
+
+## 1. Overview
+Refactor the Python codebase to a "Single-Space, Ultra-Compact" style specifically designed to minimize token consumption for AI age...
+---
+Track: Robust Live Simulation Verification
+Status: planned
+Overview: Establish a robust, visual simulation framework to prevent regressions in the complex GUI and asynchronous orchestration layers. This track replaces manual human verification with an automated script that clicks through the GUI and verifies the rendered state.
+---
+Track: session_insights_20260306
+Status: planned
+Overview: Token usage over time, cost projections, session summary with efficiency scores. Visualize session_logger data.
+---
+Track: simulation_hardening_20260301
+Status: new
+Overview: The `robust_live_simulation_verification` track is marked complete but its session compression documents three unresolved issues: (1) brittle mock that triggers the wrong approval popup, (2) popup state desynchronization after "Accept" clicks, (3) Tier 3 output never appearing in `mma_streams` (fixed by `mma_pipeline_fix` track). This track stabilizes the simulation framework so it reliably passes end-to-end.
+---
+Track: strict_execution_queue_completed_20260306
+Status: completed
+Overview: No overview available.
+---
+Track: strict_static_analysis_and_typing_20260302
+Status: new
+Overview: The codebase currently suffers from massive type-safety debt (512+ `mypy` errors across 64 files) and lingering `ruff` violations. This track will harden the foundation by resolving all violations, enforcing strict typing (especially in `gui_2.py` and `api_hook_client.py`), and integrating pre-commit checks. This is a prerequisite for safe AI-driven refactoring.
+---
+Track: tech_debt_and_test_cleanup_20260302
+Status: new
+Overview: Due to rapid iterative development and feature bleed across multiple Tier 2-led tracks, significant tech debt has accumulated in both the testing suite and `gui_2.py`.
+This track will clean up test fixtures, enforce test assertion integrity, and remove dead codebase remnants.
+---
+Track: test_architecture_integrity_audit_20260304
+Status: unknown
+Overview: Comprehensive audit of testing infrastructure and simulation framework to identify false positive risks, coverage gaps, and simulation fidelity issues. This analysis was triggered by a request to review how tests and simulations are setup, whether tests can report passing grades when they fail, and if simulations are rigorous enough or are just rough emulators.
+---
+Track: test_curation_20260225
+Status: new
+Overview: The current test suite for **Manual Slop** and the **Conductor** framework has grown incrementally and lacks a formal organization. This track aims to curate, categorize, and organize existing tests, specifically blacklisting Conductor-specific (MMA) tests from manual_slop's test runs. We will use a central manifest for test management and perform an exhaustive review of all tests to eliminate redundancy.
+---
+Track: test_hooks_20260223
+Status: new
+Overview: This track introduces a comprehensive suite of API hooks designed specifically for the Gemini CLI and the Conductor framework. These hooks will allow automated agents to manipulate and test the internal state of the application without requiring manual GUI interaction, enabling automated test-driven development and track progression validation.
+---
+Track: Test Integrity Audit & Intent Documentation
+Status: in_progress
+Overview: Audit and fix tests that have been "simplified" or "dumbed down" by AI agents, restoring their original verification intent through explicit documentation comments. This track addresses the growing problem of AI agents "completing" tasks by weakening test assertions rather than implementing proper functionality.
+---
+Track: test_regression_verification_20260307
+Status: unknown
+Overview: Verify that all existing tests pass with 0 regressions after recent track implementations (Kill/Abort, Block/Unblock, Pause/Resume, Per-Ticket Model Override).
+---
+Track: test_stabilization_20260302
+Status: new
+Overview: The goal of this track is to stabilize and unify the project's test suite. This involves resolving pervasive `asyncio` lifecycle errors, consolidating redundant testing paradigms (specifically manual GUI subprocesses), ensuring artifact isolation in `./tests/artifacts/`, implementing functional assertions for currently mocked-out tests, and updating documentation to reflect the finalized verification framework.
+---
+Track: ticket_queue_mgmt_20260306
+Status: planned
+Overview: Allow user to manually reorder, prioritize, or requeue tickets in the DAG. Add drag-drop reordering, priority tags, and bulk selection for execute/skip/block operations.
+---
+Track: tier4_auto_patching_20260306
+Status: planned
+Overview: Elevate Tier 4 from log summarizer to auto-patcher. When verification tests fail, Tier 4 generates a unified diff patch. GUI displays side-by-side diff; user clicks Apply Patch to resume pipeline.
+---
+Track: Tiered Context Scoping & HITL Approval
+Status: planned
+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.
+---
+Track: tool_usage_analytics_20260306
+Status: planned
+Overview: Analytics panel showing most-used tools, average execution time, and failure rates. Uses existing tool execution data from ai_client.
+---
+Track: track_progress_viz_20260306
+Status: planned
+Overview: Progress bars and percentage completion for active tracks and tickets. Better visualization of DAG execution state.
+---
+Track: true_parallel_worker_execution_20260306
+Status: planned
+Overview: Add worker pool management and configurable concurrency limits to the DAG engine. Currently workers execute in parallel per tick but with no limits or tracking; this track adds max_workers configuration, worker tracking, and proper pool management.
+---
+Track: ui_performance_20260223
+Status: new
+Overview: This track aims to resolve subpar UI performance (currently perceived below 60 FPS) by implementing a robust performance monitoring system. This system will collect high-resolution telemetry (Frame Time, Input Lag, Thread Usage) and expose it to both the user (via a Diagnostics Panel) and the AI (via API hooks). This ensures that performance degradation is caught early during development and testing.
+---
+Track: visual_dag_ticket_editing_20260306
+Status: planned
+Overview: Replace linear ticket list with interactive node graph using ImGui Bundle node editor. Users can visually drag dependency lines, split nodes, or delete tasks before execution.
+---
+Track: caching_optimization_20260308
+Status: new
+Overview: This track aims to verify and optimize the caching strategies across all supported AI providers (Gemini, Anthropic, DeepSeek, MiniMax, and OpenAI). The goal is to minimize token consumption and latency by ensuring that static and recurring context (system prompts, tool definitions, project documents, and conversation history) are effectively cached using each provider's specific mechanisms.
+---
+Track: codebase_audit_20260308
+Status: new
+Overview: The objective of this track is to audit the `./src` and `./simulation` directories to improve human readability and maintainability. The codebase has matured, and it is necessary to identify and address redundant code paths and state tracking, add missing docstrings to critical paths, and organize declarations/definitions within files.
+---
+Track: conductor_path_configurable_20260306
+Status: unknown
+Overview: Eliminate all hardcoded paths in the application. Make directory paths configurable via `config.toml` or environment variables, allowing the running app to use different directories from development setup. This is **Phase 0 - Critical Infrastructure** that must be completed before other Phase 3 tracks.
+---
+Track: external_editor_integration_20260308
+Status: new
+Overview: This feature adds the ability to open files modified by AI agents in external text editors (such as VSCode or 10xNotepad) directly from the tool approval popup. This allows users to leverage their preferred editor's native diffing and editing capabilities before confirming an agent's changes.
+---
+Track: external_mcp_support_20260308
+Status: new
+Overview: This feature adds support for integrating external Model Context Protocol (MCP) servers into Manual Slop. This allows agents to utilize tools from a wide ecosystem of MCP servers (like those for databases, APIs, or specialized utilities) alongside the application's native tools.
+---
+Track: Bootstrap gencpp Python Bindings Project
+Status: pending
+Overview: Create a new standalone Python project to build CFFI bindings for gencpp (C/C++ staged metaprogramming library). This will eventually provide richer C++ AST understanding than tree-sitter (full type information, operators, specifiers) but is a longer-term effort. This track bootstraps the project structure and initial bindings.
+---
+Track: GUI Path Configuration in Context Hub
+Status: pending
+Overview: Add path configuration UI to the Context Hub in the GUI. Allow users to view and edit configurable paths (conductor, logs, scripts) directly from the application without manually editing config.toml or environment variables.
+---
+Track: hook_api_expansion_20260308
+Status: new
+Overview: This track aims to transform the Manual Slop Hook API into a comprehensive control plane for headless use. It focuses on exposing all relevant internal states (worker traces, AST metadata, financial metrics, concurrency telemetry) and providing granular control over the application's lifecycle, MMA pipeline, and context management. Additionally, it introduces a WebSocket-based streaming interface for real-time event delivery.
+---
+Track: log_session_overhaul_20260308
+Status: new
+Overview: This track focuses on centralizing log management, improving the reliability and scope of session restoration, and optimizing log storage by offloading large data blobs (scripts and tool outputs) to external files. It also aims to "clean" the discussion history by moving transient system warnings to a dedicated diagnostic log.
+---
+Track: manual_ux_validation_20260302
+Status: new
+Overview: This track is an unusual, highly interactive human-in-the-loop review session. The user will act as the primary QA and Designer, manually using the GUI and observing it during slow-interval simulation runs. The goal is to aggressively iterate on the "feel" of the application: analyzing blinking animations, structural decisions (Tabs vs. Panels vs. Collapsing Headers), knob/control placements, and the efficacy of popups (including adding auto-close timers).
+---
+Track: markdown_highlighting_20260308
+Status: new
+Overview: This track introduces rich text rendering to the Manual Slop GUI by adding support for GitHub-Flavored Markdown (GFM) in message and response views. It also adds syntax highlighting for code blocks and text content when the language context can be cheaply resolved (e.g., via known metadata or file extensions).
+---
+Track: openai_integration_20260308
+Status: new
+Overview: This track introduces support for OpenAI as a first-class model provider. It involves implementing a dedicated client in `src/ai_client.py`, updating configuration models, enhancing the GUI for provider selection, and integrating OpenAI into the tiered MMA architecture.
+---
+Track: Project-Specific Conductor Directory
+Status: pending
+Overview: Make the conductor directory per-project instead of global. Each project TOML can specify its own `conductor_dir` path, allowing separate track/state management per project. This enables using Manual Slop with multiple independent projects without track/ticket cross-pollution.
+---
+Track: rag_support_20260308
+Status: new
+Overview: This track introduces Retrieval-Augmented Generation (RAG) capabilities to Manual Slop. It allows agents to search and retrieve relevant information from large local codebases, project documentation, or external knowledge bases, overcoming context window limitations and reducing hallucination.
+---
+Track: saved_presets_20260308
+Status: new
+Overview: This feature introduces the ability to save, manage, and switch between system prompt presets for both global (application-wide) and project-specific contexts. Presets will include not only the system prompt text but also model-specific parameters like temperature and top_p, effectively allowing for "AI Profiles."
+---
+Track: saved_tool_presets_20260308
+Status: new
+Overview: This feature adds the ability to create, save, and manage "Tool Presets" for agent roles. These presets define which tools are available to an agent and their respective "auto" vs "ask" approval levels. Tools will be organized into dynamic, TOML-defined categories (e.g., Python, General) and integrated into the global and project-specific AI settings.
+---
+Track: selectable_ui_text_20260308
+Status: new
+Overview: This track aims to address UI inconveniences by making critical text across the GUI selectable and copyable. This includes discussion history, communication logs, tool outputs, and key metrics. The goal is to provide a standard "Copy to Clipboard" capability via OS-native selection and shortcuts (Ctrl+C).
+---
+Track: tool_bias_tuning_20260308
+Status: new
+Overview: This track introduces a mechanism to influence AI agent tool selection by implementing a weighting and scoring system at the orchestration layer. Since model APIs do not natively support tool priority, this feature uses semantic nudging (tags in tool descriptions) and explicit system instructions to "bias" the agent toward preferred tools and parameters.
+---
+Track: Tree-Sitter C/C++ MCP Tools
+Status: pending
+Overview: Add tree-sitter-based C and C++ parsing support to the MCP client, providing skeleton and outline tools for C/C++ codebases. Tools will be prefixed `ts_c_` and `ts_cpp_` to distinguish from existing Python tools and leave namespace open for future gencpp integration.
+---
+Track: ui_theme_overhaul_20260308
+Status: new
+Overview: This track aims to modernize the application's appearance by implementing a professional, high-fidelity UI theme using `imgui-bundle`'s native styling and theming capabilities. It focuses on improving typography, visual shapes, and introducing advanced features like custom shaders, multi-viewport support, and user-managed layout presets.
+---
+Track: zhipu_integration_20260308
+Status: new
+Overview: This track introduces support for Zhipu AI (z.ai) as a first-class model provider. It involves implementing a dedicated client in `src/ai_client.py` for the GLM series of models, updating configuration models, enhancing the GUI for provider selection, and integrating the provider into the tiered MMA architecture.
+---
+
+Please generate the implementation tracks for this request.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+PATH: Epic Initialization — please produce tracks
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please generate the implementation tickets for this track.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please read test.txt
+You are assigned to Ticket T1.
+Task Description: do something
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+role: tool
+Here are the results: {"content": "done"}
+------------------
+--- MOCK INVOKED ---
+ARGS: ['C:\\projects\\manual_slop\\tests\\mock_gemini_cli.py', '-m', 'gemini-2.5-flash-lite', '--prompt', '', '--output-format', 'stream-json']
+PROMPT:
+You are a helpful coding assistant with access to a PowerShell tool (run_powershell) and MCP tools (file access: read_file, list_directory, search_files, get_file_summary, web access: web_search, fetch_url). When calling file/directory tools, always use the 'path' parameter for the target path. When asked to create or edit files, prefer targeted edits over full rewrites. Always explain what you are doing before invoking the tool.
+
+When writing or rewriting large files (especially those containing quotes, backticks, or special characters), avoid python -c with inline strings. Instead: (1) write a .py helper script to disk using a PS here-string (@'...'@ for literal content), (2) run it with `python <script>`, (3) delete the helper. For small targeted edits, use PowerShell's (Get-Content) / .Replace() / Set-Content or Add-Content directly.
+
+When making function calls using tools that accept array or object parameters ensure those are structured using JSON. For example:
+When you need to verify a change, rely on the exit code and stdout/stderr from the tool — the user's context files are automatically refreshed after every tool call, so you do NOT need to re-read files that are already provided in the <context> block.
+
+[USER SYSTEM PROMPT]
+
+You are the Tier 1 Orchestrator (Product Manager) for the Manual Slop project.
+Your role is high-level strategic planning, architecture enforcement, and cross-module delegation.
+You operate strictly on metadata, summaries, and executive-level directives.
+NEVER request or attempt to read raw implementation code unless specifically provided in a Macro-Diff.
+Maintain a "Godot ECS Flat List format" (JSON array of objects) for structural outputs.
+
+PATH: Epic Initialization (Project Planning)
+GOAL: Break down a massive feature request into discrete Implementation Tracks.
+
+CONSTRAINTS:
+- IGNORE all source code, AST skeletons, and previous micro-task histories.
+- FOCUS ONLY on the Repository Map and Project Meta-State.
+
+OUTPUT REQUIREMENT:
+Return a JSON array of 'Tracks'. Each track object must follow the Godot ECS Flat List format:
+[
+  {
+    "id": "track_unique_id",
+    "type": "Track",
+    "module": "target_module_name",
+    "persona": "required_tech_lead_persona",
+    "severity": "Low|Medium|High",
+    "goal": "Descriptive goal",
+    "acceptance_criteria": ["criteria_1", "criteria_2"]
+  },
+  ...
+]
+
+
+<context>
+
+</context>
+
+### USER REQUEST:
+Add timestamps
+
+### REPOSITORY MAP:
+
+
+### TRACK HISTORY:
+Track: api_hooks_verification_20260223
+Status: new
+Overview: This track focuses on integrating the existing, previously implemented API hooks (from track `test_hooks_20260223`) into the Conductor workflow. The primary goal is to automate the verification steps within the "Phase Completion Verification and Checkpointing Protocol", reducing the need for manual user intervention and enabling a more streamlined, automated development process.
+---
+Track: api_metrics_20260223
+Status: new
+Overview: This track aims to optimize token efficiency and transparency by reviewing and improving how vendor APIs (Gemini and Anthropic) handle conservative context pruning. The primary focus is on extracting, plotting, and exposing deep metrics to the GUI so developers can intuit how close they are to API limits (e.g., token caps, cache counts, history bleed).
+---
+Track: api_vendor_alignment_20260223
+Status: new
+Overview: This track involves a comprehensive audit of the "Manual Slop" codebase to ensure that the integration with Google Gemini (`google-genai`) and Anthropic Claude (`anthropic`) SDKs aligns perfectly with their latest official documentation and best practices. The goal is to identify discrepancies, performance bottlenecks, or deprecated patterns and implement the necessary fixes.
+---
+Track: architecture_boundary_hardening_20260302
+Status: new
+Overview: The `manual_slop` project sandbox provides AI meta-tooling (`mma_exec.py`, `tool_call.py`) to orchestrate its own development. When AI agents added advanced AST tools (like `set_file_slice`) to `mcp_client.py` for meta-tooling, they failed to fully integrate them into the application's GUI, config, or HITL (Human-In-The-Loop) safety models. Additionally, meta-tooling scripts are bleeding tokens and rely on non-portable hardcoded machine paths, while the internal application's state machine can deadlock.
+---
+Track: cache_analytics_20260306
+Status: planned
+Overview: Gemini cache hit/miss visualization, memory usage, TTL status display. Uses existing `ai_client.get_gemini_cache_stats()` which is implemented but has no GUI representation.
+---
+Track: codebase_migration_20260302
+Status: new
+Overview: This track focuses on restructuring the codebase to alleviate clutter by moving the main implementation files from the project root into a dedicated `src/` directory. Additionally, files that are completely unused by the current implementation will be automatically identified and removed. A new clean entry point (`sloppy.py`) will be created in the root directory.
+---
+Track: comprehensive_gui_ux_20260228
+Status: completed
+Overview: This track enhances the existing MMA orchestration GUI from its current functional-but-minimal state to a production-quality control surface. The existing implementation already has a working Track Browser, DAG tree visualizer, epic planning flow, approval dialogs, and token usage table. This track focuses on the **gaps**: dedicated tier stream panels, DAG editing, track-scoped discussions, conductor lifecycle GUI forms, cost tracking, and visual polish.
+---
+Track: conductor_workflow_improvements_20260302
+Status: new
+Overview: Recent Tier 2 track implementations have resulted in feature bleed, redundant code, unread state variables, and degradation of TDD discipline (e.g., zero-assertion tests).
+This track updates the Conductor documentation (`workflow.md`) and the Gemini skills for Tiers 2 and 3 to hard-enforce TDD, prevent hallucinated "mock" implementations, and enforce strict codebase auditing before writing code.
+---
+Track: consolidate_cruft_and_log_taxonomy_20260228
+Status: unknown
+Overview: This track focuses on cleaning up the project root by consolidating temporary and test-related files into a dedicated directory and establishing a structured taxonomy for session logs. This will improve project organization and make manual file exploration easier before a dedicated GUI log viewer is implemented.
+---
+Track: context_management_20260223
+Status: new
+Overview: This track implements UI improvements and structural changes to Manual Slop to provide explicit visualization of context memory usage and token consumption, fulfilling the "Expert systems level utility" and "Full control" product goals.
+---
+Track: context_token_viz_20260301
+Status: new
+Overview: product.md lists "Context & Memory Management" as primary use case #2: "Better visualization and management of token usage and context memory, allowing developers to optimize prompt limits manually." The backend already computes everything needed via `ai_client.get_history_bleed_stats()` (ai_client.py:1657-1796, 140 lines). This track builds the UI to expose it.
+---
+Track: cost_token_analytics_20260306
+Status: planned
+Overview: # Implementation Plan: Cost & Token Analytics Panel (cost_token_analytics_20260306)
+
+> **Reference:** [Spec](./spec.md) | [Architecture Guide](../../../docs/guide_architecture.md)
+
+## Phase 1: Foundat...
+---
+Track: deepseek_support_20260225
+Status: new
+Overview: Implement a new AI provider module to support the DeepSeek API within the Manual Slop application. This integration will leverage a dedicated SDK to provide access to high-performance models (DeepSeek-V3 and DeepSeek-R1) with support for streaming, tool calling, and detailed reasoning traces.
+---
+Track: deep_ast_context_pruning_20260306
+Status: planned
+Overview: Use tree_sitter to parse target file AST and inject condensed skeletons into worker prompts. Currently workers receive full file context; this track reduces token burn by injecting only relevant function/method signatures.
+---
+Track: documentation_refresh_20260224
+Status: new
+Overview: This track implements a high-density, expert-level documentation suite for the Manual Slop project. The documentation style is strictly modeled after the **pedagogical and narrative standards** of `gencpp` and `VEFontCache-Odin`. It moves beyond simple "User Guides" to provide a **"USA Graphics Company"** architectural reference: high information density, tactical technical transparency, and a narrative intent that guides a developer from high-level philosophy to low-level implementation.
+---
+Track: enhanced_context_control_20260307
+Status: planned
+Overview: Give developers granular control over how files are included in the AI context and provide visibility into the active Gemini cache state. This involves moving away from a simple list of files to a structured format with per-file flags (`auto_aggregate`, `force_full`), revamping the UI to display this state, and updating the context builders and API clients to respect and expose these details.
+---
+Track: event_driven_metrics_20260223
+Status: new
+Overview: Refactor the API metrics update mechanism to be event-driven. Currently, the UI likely polls or recalculates metrics on every frame. This track will implement a signal/event system where `ai_client.py` broadcasts updates only when significant API activities (requests, responses, tool calls, or stream chunks) occur.
+---
+Track: feature_bleed_cleanup_20260302
+Status: new
+Overview: Multiple tracks added code to `gui_2.py` without removing the old versions, leaving
+dead duplicate methods, conflicting menu bar designs, and redundant state initializations.
+This track removes confirmed dead code, resolves the two-menubar conflict, and cleans
+up the token budget layout regression — restoring a consistent, non-contradictory design state.
+---
+Track: gemini_cli_headless_20260224
+Status: new
+Overview: This track integrates the `gemini` CLI as a headless backend provider for Manual Slop. This allows users to leverage their Gemini subscription and the CLI's advanced features (e.g., specialized sub-agents like `codebase_investigator`, structured JSON streaming, and robust session management) directly within the Manual Slop GUI.
+---
+Track: gemini_cli_parity_20260225
+Status: new
+Overview: Achieve full functional and behavioral parity between the Gemini CLI integration (`gemini_cli_adapter.py`, `cli_tool_bridge.py`) and the direct Gemini API implementation (`ai_client.py`). This ensures that users leveraging the Gemini CLI as a headless backend provider experience the same level of capability, reliability, and observability as direct API users.
+---
+Track: gui2_feature_parity_20260223
+Status: new
+Overview: # Specification: GUIv2 Feature Parity
+
+## 1. Overview
+
+This track aims to bring `gui_2.py` (the `imgui-bundle` based UI) to feature parity with the existing `gui.py` (the `dearpygui` based UI). This i...
+---
+Track: gui2_parity_20260224
+Status: new
+Overview: The project is transitioning from `gui.py` (Dear PyGui-based) to `gui_2.py` (ImGui Bundle-based) to leverage advanced multi-viewport and docking features not natively supported by Dear PyGui. This track focuses on achieving full visual, functional, and performance parity between the two implementations, ultimately enabling the decommissioning of the original `gui.py`.
+---
+Track: gui_decoupling_controller_20260302
+Status: new
+Overview: `gui_2.py` currently operates as a Monolithic God Object (3,500+ lines). It violates the Data-Oriented Design heuristic by owning complex business logic, orchestrator hooks, and markdown file building. This track extracts the core state machine and lifecycle into a headless `app_controller.py`, turning the GUI into a pure immediate-mode view.
+---
+Track: gui_layout_refinement_20260223
+Status: new
+Overview: This track focuses on a holistic review and reorganization of the Manual Slop GUI. The goal is to ensure that AI tunings, diagnostic features, context management, and discussion history are logically placed to support an expert-level "Multi-Viewport" workflow. We will strengthen the "Arcade Aesthetics" and "Tactile Density" values while ensuring the layout remains intuitive for power users.
+---
+Track: gui_performance_20260223
+Status: new
+Overview: This track focuses on identifying and resolving severe frametime performance issues in the Manual Slop GUI. Current observations indicate massive frametime bloat even on idle startup, with performance significantly regressing (target 60 FPS / <16.6ms) since commit `8aa70e287fbf93e669276f9757965d5a56e89b10`.
+---
+Track: gui_performance_profiling_20260307
+Status: unknown
+Overview: Implement fine-grained performance profiling within the main ImGui rendering loop (`gui_2.py`) to ensure adherence to data-oriented and immediate mode heuristics. This track will provide visual diagnostics for high-overhead UI components, allowing developers to monitor and optimize render frame times.
+---
+Track: gui_sim_extension_20260224
+Status: new
+Overview: This track aims to expand the test simulation suite by introducing comprehensive, in-breadth tests that cover all facets of the GUI interaction. The original small test simulation will be preserved as a useful baseline. The new extended tests will be structured as multiple focused, modular scripts rather than a single long-running journey, ensuring maintainability and targeted coverage.
+---
+Track: history_segregation_20260224
+Status: new
+Overview: Currently, `manual_slop.toml` stores both project configuration and the entire discussion history. This leads to redundancy and potential context bloat if the AI agent reads the raw TOML file via its tools. This track will move the discussion history to a dedicated sibling TOML file (`history.toml`) and strictly blacklist it from the AI agent's file tools to ensure it only interacts with the curated context provided in the prompt.
+---
+Track: kill_abort_workers_20260306
+Status: planned
+Overview: Add ability to kill/abort a running Tier 3 worker mid-execution. Currently workers run to completion; add cancel button with forced termination option.
+---
+Track: live_gui_testing_20260223
+Status: new
+Overview: Update the testing suite to ensure all tests (especially GUI-related and integration tests) communicate with a live running instance of `gui.py` started with the `--enable-test-hooks` argument. This ensures that tests can verify the actual application state and metrics via the built-in API hooks.
+---
+Track: live_ux_test_20260223
+Status: new
+Overview: This track implements a robust, "human-like" interaction test suite for Manual Slop. The suite will simulate a real user's workflow—from project creation to complex AI discussions and history management—using the application's API hooks. It aims to verify the "Integrated Workspace" functionality, tool execution, and history persistence without requiring manual human input, while remaining slow enough for visual audit.
+---
+Track: logging_refactor_20260226
+Status: new
+Overview: Currently, `gui_2.py` and the test suites generate a large number of log files in a flat `logs/` directory. These logs accumulate quickly, especially during incremental development and testing. This track aims to organize logs into session-based sub-directories and implement a heuristic-based pruning system to keep the log directory clean while preserving valuable sessions.
+---
+Track: manual_block_control_20260306
+Status: planned
+Overview: Allow user to manually block or unblock tickets with custom reasons. Currently blocked tickets rely solely on dependency resolution; add manual override capability.
+---
+Track: manual_skeleton_injection_20260306
+Status: planned
+Overview: Add UI controls to manually inject file skeletons into discussions. Allow user to preview skeleton content before sending to AI, with option to toggle between skeleton and full file.
+---
+Track: manual_slop_headless_20260225
+Status: new
+Overview: Transform Manual Slop into a decoupled, container-friendly backend service. This track enables the core AI orchestration and tool execution logic to run without a GUI, exposing its capabilities via a secured REST API optimized for an Unraid Docker environment.
+---
+Track: minimax_provider_20260306
+Status: unknown
+Overview: Add MiniMax as a new AI provider to Manual Slop. MiniMax provides high-performance text generation models (M2.5, M2.1, M2) with massive context windows (200k+ tokens) and competitive pricing.
+---
+Track: mma_agent_focus_ux_20260302
+Status: new
+Overview: All MMA observability panels (comms history, tool calls, discussion) display
+global/session-scoped data. When 4 tiers are running concurrently, their traffic
+is indistinguishable. This track adds a `source_tier` field to every comms and
+tool log entry at the point of emission, then adds a "Focus Agent" selector that
+filters the Operations Hub panels to show only one tier's traffic at a time.
+
+**Depends on:** `feature_bleed_cleanup_20260302` (Phase 1 removes the dead comms
+panel duplicate; this track extends the live panel at gui_2.py:~3400).
+---
+Track: MMA Core Engine Implementation
+Status: planning
+Overview: # Specification: MMA Core Engine Implementation
+
+## 1. Overview
+This track consolidates the implementation of the 4-Tier Hierarchical Multi-Model Architecture into the `manual_slop` codebase. The arch...
+---
+Track: MMA Dashboard Visualization Overhaul
+Status: planned
+Overview: Make the invisible backend operations visible and interactive. The current GUI is too barebones to effectively manage a multi-agent system. This track overhauls the MMA Dashboard to provide real-time insights into tracks, task dependencies, and agent streams.
+---
+Track: MMA Data Architecture & DAG Engine
+Status: planned
+Overview: Restructure how `manual_slop` stores and executes work. The current implementation relies on global state and linear execution, which does not support the complexity of multi-agent, task-based workflows. This track establishes a robust, data-oriented foundation using track-scoped state and a native Python Directed Acyclic Graph (DAG) engine.
+---
+Track: mma_formalization_20260225
+Status: new
+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.
+---
+Track: mma_implementation_20260224
+Status: new
+Overview: # Specification: 4-Tier Architecture Implementation & Conductor Self-Improvement
+
+## 1. Overview
+This track encompasses two major phases. Phase 1 focuses on designing a comprehensive, step-by-step imp...
+---
+Track: mma_multiworker_viz_20260306
+Status: planned
+Overview: Split-view GUI for parallel worker streams per tier. Visualize multiple concurrent workers with individual status, output tabs, and resource usage. Enable kill/restart per worker.
+---
+Track: MMA Orchestrator Integration
+Status: in-progress
+Overview: Implement the full hierarchical orchestration loop, connecting Tier 1 (PM) strategic planning with Tier 2 (Tech Lead) tactical ticket generation. This track will enable the GUI to autonomously break down high-level user 'Epics' into actionable tracks and tickets, and manage their execution through the multi-agent system.
+---
+Track: mma_pipeline_fix_20260301
+Status: new
+Overview: The MMA pipeline has a verified code path from `run_worker_lifecycle` → `_queue_put("response", ...)` → `_process_event_queue` → `_pending_gui_tasks("handle_ai_response")` → `mma_streams[stream_id] = text`. However, the robust_live_simulation track's session compression (2026-02-28) documented that Tier 3 worker output never appears in `mma_streams` during actual GUI operation. The simulation only ever sees `'Tier 1'` in `mma_streams` keys.
+
+This track diagnoses and fixes the pipeline break, then verifies end-to-end that worker output flows from `ai_client.send()` through to the GUI's `mma_streams` dict.
+---
+Track: mma_utilization_refinement_20260226
+Status: new
+Overview: Refine the Multi-Model Architecture (MMA) implementation within the Conductor framework to ensure clear role segregation, proper tool permissions, and improved observability for sub-agents.
+---
+Track: mma_verification_20260225
+Status: new
+Overview: This track aims to review and verify the implementation of the 4-Tier Hierarchical Multi-Model Architecture (MMA) within the Conductor framework. It will confirm that Conductor operates as a Tier 2 Tech Lead/Orchestrator and can successfully delegate tasks to Tier 3 (Workers) and Tier 4 (QA/Utility) sub-agents. A key part of this track is investigating whether this hierarchy should be enforced via a single centralized skill or through separate role-based sub-agent definitions.
+---
+Track: mma_verification_mock
+Status: new
+Overview: This is a mock track designed to verify the full Tier 2 -> Tier 3 -> Tier 4 delegation flow within the Conductor framework.
+---
+Track: native_orchestrator_20260306
+Status: planned
+Overview: Absorb `mma_exec.py` functionality into core application. Manual Slop natively reads/writes plan.md, manages metadata.json, and orchestrates MMA tiers in pure Python without external CLI subprocess calls.
+---
+Track: on_demand_def_lookup_20260306
+Status: planned
+Overview: Add ability for agent to request specific class/function definitions during discussion. Parse @symbol syntax to trigger lookup and display inline in the discussion.
+---
+Track: per_ticket_model_20260306
+Status: planned
+Overview: Allow user to manually select which model to use for a specific ticket, overriding the default tier model. Useful for forcing smarter model on hard tickets.
+---
+Track: pipeline_pause_resume_20260306
+Status: planned
+Overview: Add global pause/resume for entire DAG execution pipeline. Allow user to freeze all worker activity and resume later without losing state.
+---
+Track: python_style_refactor_20260227
+Status: unknown
+Overview: # Specification: AI-Optimized Python Style Refactor
+
+## 1. Overview
+Refactor the Python codebase to a "Single-Space, Ultra-Compact" style specifically designed to minimize token consumption for AI age...
+---
+Track: Robust Live Simulation Verification
+Status: planned
+Overview: Establish a robust, visual simulation framework to prevent regressions in the complex GUI and asynchronous orchestration layers. This track replaces manual human verification with an automated script that clicks through the GUI and verifies the rendered state.
+---
+Track: session_insights_20260306
+Status: planned
+Overview: Token usage over time, cost projections, session summary with efficiency scores. Visualize session_logger data.
+---
+Track: simulation_hardening_20260301
+Status: new
+Overview: The `robust_live_simulation_verification` track is marked complete but its session compression documents three unresolved issues: (1) brittle mock that triggers the wrong approval popup, (2) popup state desynchronization after "Accept" clicks, (3) Tier 3 output never appearing in `mma_streams` (fixed by `mma_pipeline_fix` track). This track stabilizes the simulation framework so it reliably passes end-to-end.
+---
+Track: strict_execution_queue_completed_20260306
+Status: completed
+Overview: No overview available.
+---
+Track: strict_static_analysis_and_typing_20260302
+Status: new
+Overview: The codebase currently suffers from massive type-safety debt (512+ `mypy` errors across 64 files) and lingering `ruff` violations. This track will harden the foundation by resolving all violations, enforcing strict typing (especially in `gui_2.py` and `api_hook_client.py`), and integrating pre-commit checks. This is a prerequisite for safe AI-driven refactoring.
+---
+Track: tech_debt_and_test_cleanup_20260302
+Status: new
+Overview: Due to rapid iterative development and feature bleed across multiple Tier 2-led tracks, significant tech debt has accumulated in both the testing suite and `gui_2.py`.
+This track will clean up test fixtures, enforce test assertion integrity, and remove dead codebase remnants.
+---
+Track: test_architecture_integrity_audit_20260304
+Status: unknown
+Overview: Comprehensive audit of testing infrastructure and simulation framework to identify false positive risks, coverage gaps, and simulation fidelity issues. This analysis was triggered by a request to review how tests and simulations are setup, whether tests can report passing grades when they fail, and if simulations are rigorous enough or are just rough emulators.
+---
+Track: test_curation_20260225
+Status: new
+Overview: The current test suite for **Manual Slop** and the **Conductor** framework has grown incrementally and lacks a formal organization. This track aims to curate, categorize, and organize existing tests, specifically blacklisting Conductor-specific (MMA) tests from manual_slop's test runs. We will use a central manifest for test management and perform an exhaustive review of all tests to eliminate redundancy.
+---
+Track: test_hooks_20260223
+Status: new
+Overview: This track introduces a comprehensive suite of API hooks designed specifically for the Gemini CLI and the Conductor framework. These hooks will allow automated agents to manipulate and test the internal state of the application without requiring manual GUI interaction, enabling automated test-driven development and track progression validation.
+---
+Track: Test Integrity Audit & Intent Documentation
+Status: in_progress
+Overview: Audit and fix tests that have been "simplified" or "dumbed down" by AI agents, restoring their original verification intent through explicit documentation comments. This track addresses the growing problem of AI agents "completing" tasks by weakening test assertions rather than implementing proper functionality.
+---
+Track: test_regression_verification_20260307
+Status: unknown
+Overview: Verify that all existing tests pass with 0 regressions after recent track implementations (Kill/Abort, Block/Unblock, Pause/Resume, Per-Ticket Model Override).
+---
+Track: test_stabilization_20260302
+Status: new
+Overview: The goal of this track is to stabilize and unify the project's test suite. This involves resolving pervasive `asyncio` lifecycle errors, consolidating redundant testing paradigms (specifically manual GUI subprocesses), ensuring artifact isolation in `./tests/artifacts/`, implementing functional assertions for currently mocked-out tests, and updating documentation to reflect the finalized verification framework.
+---
+Track: ticket_queue_mgmt_20260306
+Status: planned
+Overview: Allow user to manually reorder, prioritize, or requeue tickets in the DAG. Add drag-drop reordering, priority tags, and bulk selection for execute/skip/block operations.
+---
+Track: tier4_auto_patching_20260306
+Status: planned
+Overview: Elevate Tier 4 from log summarizer to auto-patcher. When verification tests fail, Tier 4 generates a unified diff patch. GUI displays side-by-side diff; user clicks Apply Patch to resume pipeline.
+---
+Track: Tiered Context Scoping & HITL Approval
+Status: planned
+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.
+---
+Track: tool_usage_analytics_20260306
+Status: planned
+Overview: Analytics panel showing most-used tools, average execution time, and failure rates. Uses existing tool execution data from ai_client.
+---
+Track: track_progress_viz_20260306
+Status: planned
+Overview: Progress bars and percentage completion for active tracks and tickets. Better visualization of DAG execution state.
+---
+Track: true_parallel_worker_execution_20260306
+Status: planned
+Overview: Add worker pool management and configurable concurrency limits to the DAG engine. Currently workers execute in parallel per tick but with no limits or tracking; this track adds max_workers configuration, worker tracking, and proper pool management.
+---
+Track: ui_performance_20260223
+Status: new
+Overview: This track aims to resolve subpar UI performance (currently perceived below 60 FPS) by implementing a robust performance monitoring system. This system will collect high-resolution telemetry (Frame Time, Input Lag, Thread Usage) and expose it to both the user (via a Diagnostics Panel) and the AI (via API hooks). This ensures that performance degradation is caught early during development and testing.
+---
+Track: visual_dag_ticket_editing_20260306
+Status: planned
+Overview: Replace linear ticket list with interactive node graph using ImGui Bundle node editor. Users can visually drag dependency lines, split nodes, or delete tasks before execution.
+---
+Track: caching_optimization_20260308
+Status: new
+Overview: This track aims to verify and optimize the caching strategies across all supported AI providers (Gemini, Anthropic, DeepSeek, MiniMax, and OpenAI). The goal is to minimize token consumption and latency by ensuring that static and recurring context (system prompts, tool definitions, project documents, and conversation history) are effectively cached using each provider's specific mechanisms.
+---
+Track: codebase_audit_20260308
+Status: new
+Overview: The objective of this track is to audit the `./src` and `./simulation` directories to improve human readability and maintainability. The codebase has matured, and it is necessary to identify and address redundant code paths and state tracking, add missing docstrings to critical paths, and organize declarations/definitions within files.
+---
+Track: conductor_path_configurable_20260306
+Status: unknown
+Overview: Eliminate all hardcoded paths in the application. Make directory paths configurable via `config.toml` or environment variables, allowing the running app to use different directories from development setup. This is **Phase 0 - Critical Infrastructure** that must be completed before other Phase 3 tracks.
+---
+Track: external_editor_integration_20260308
+Status: new
+Overview: This feature adds the ability to open files modified by AI agents in external text editors (such as VSCode or 10xNotepad) directly from the tool approval popup. This allows users to leverage their preferred editor's native diffing and editing capabilities before confirming an agent's changes.
+---
+Track: external_mcp_support_20260308
+Status: new
+Overview: This feature adds support for integrating external Model Context Protocol (MCP) servers into Manual Slop. This allows agents to utilize tools from a wide ecosystem of MCP servers (like those for databases, APIs, or specialized utilities) alongside the application's native tools.
+---
+Track: Bootstrap gencpp Python Bindings Project
+Status: pending
+Overview: Create a new standalone Python project to build CFFI bindings for gencpp (C/C++ staged metaprogramming library). This will eventually provide richer C++ AST understanding than tree-sitter (full type information, operators, specifiers) but is a longer-term effort. This track bootstraps the project structure and initial bindings.
+---
+Track: GUI Path Configuration in Context Hub
+Status: pending
+Overview: Add path configuration UI to the Context Hub in the GUI. Allow users to view and edit configurable paths (conductor, logs, scripts) directly from the application without manually editing config.toml or environment variables.
+---
+Track: hook_api_expansion_20260308
+Status: new
+Overview: This track aims to transform the Manual Slop Hook API into a comprehensive control plane for headless use. It focuses on exposing all relevant internal states (worker traces, AST metadata, financial metrics, concurrency telemetry) and providing granular control over the application's lifecycle, MMA pipeline, and context management. Additionally, it introduces a WebSocket-based streaming interface for real-time event delivery.
+---
+Track: log_session_overhaul_20260308
+Status: new
+Overview: This track focuses on centralizing log management, improving the reliability and scope of session restoration, and optimizing log storage by offloading large data blobs (scripts and tool outputs) to external files. It also aims to "clean" the discussion history by moving transient system warnings to a dedicated diagnostic log.
+---
+Track: manual_ux_validation_20260302
+Status: new
+Overview: This track is an unusual, highly interactive human-in-the-loop review session. The user will act as the primary QA and Designer, manually using the GUI and observing it during slow-interval simulation runs. The goal is to aggressively iterate on the "feel" of the application: analyzing blinking animations, structural decisions (Tabs vs. Panels vs. Collapsing Headers), knob/control placements, and the efficacy of popups (including adding auto-close timers).
+---
+Track: markdown_highlighting_20260308
+Status: new
+Overview: This track introduces rich text rendering to the Manual Slop GUI by adding support for GitHub-Flavored Markdown (GFM) in message and response views. It also adds syntax highlighting for code blocks and text content when the language context can be cheaply resolved (e.g., via known metadata or file extensions).
+---
+Track: openai_integration_20260308
+Status: new
+Overview: This track introduces support for OpenAI as a first-class model provider. It involves implementing a dedicated client in `src/ai_client.py`, updating configuration models, enhancing the GUI for provider selection, and integrating OpenAI into the tiered MMA architecture.
+---
+Track: Project-Specific Conductor Directory
+Status: pending
+Overview: Make the conductor directory per-project instead of global. Each project TOML can specify its own `conductor_dir` path, allowing separate track/state management per project. This enables using Manual Slop with multiple independent projects without track/ticket cross-pollution.
+---
+Track: rag_support_20260308
+Status: new
+Overview: This track introduces Retrieval-Augmented Generation (RAG) capabilities to Manual Slop. It allows agents to search and retrieve relevant information from large local codebases, project documentation, or external knowledge bases, overcoming context window limitations and reducing hallucination.
+---
+Track: saved_presets_20260308
+Status: new
+Overview: This feature introduces the ability to save, manage, and switch between system prompt presets for both global (application-wide) and project-specific contexts. Presets will include not only the system prompt text but also model-specific parameters like temperature and top_p, effectively allowing for "AI Profiles."
+---
+Track: saved_tool_presets_20260308
+Status: new
+Overview: This feature adds the ability to create, save, and manage "Tool Presets" for agent roles. These presets define which tools are available to an agent and their respective "auto" vs "ask" approval levels. Tools will be organized into dynamic, TOML-defined categories (e.g., Python, General) and integrated into the global and project-specific AI settings.
+---
+Track: selectable_ui_text_20260308
+Status: new
+Overview: This track aims to address UI inconveniences by making critical text across the GUI selectable and copyable. This includes discussion history, communication logs, tool outputs, and key metrics. The goal is to provide a standard "Copy to Clipboard" capability via OS-native selection and shortcuts (Ctrl+C).
+---
+Track: tool_bias_tuning_20260308
+Status: new
+Overview: This track introduces a mechanism to influence AI agent tool selection by implementing a weighting and scoring system at the orchestration layer. Since model APIs do not natively support tool priority, this feature uses semantic nudging (tags in tool descriptions) and explicit system instructions to "bias" the agent toward preferred tools and parameters.
+---
+Track: Tree-Sitter C/C++ MCP Tools
+Status: pending
+Overview: Add tree-sitter-based C and C++ parsing support to the MCP client, providing skeleton and outline tools for C/C++ codebases. Tools will be prefixed `ts_c_` and `ts_cpp_` to distinguish from existing Python tools and leave namespace open for future gencpp integration.
+---
+Track: ui_theme_overhaul_20260308
+Status: new
+Overview: This track aims to modernize the application's appearance by implementing a professional, high-fidelity UI theme using `imgui-bundle`'s native styling and theming capabilities. It focuses on improving typography, visual shapes, and introducing advanced features like custom shaders, multi-viewport support, and user-managed layout presets.
+---
+Track: ux_sim_test_20260308
+Status: unknown
+Overview: No overview available.
+---
+Track: zhipu_integration_20260308
+Status: new
+Overview: This track introduces support for Zhipu AI (z.ai) as a first-class model provider. It involves implementing a dedicated client in `src/ai_client.py` for the GLM series of models, updating configuration models, enhancing the GUI for provider selection, and integrating the provider into the tiered MMA architecture.
+---
+
+Please generate the implementation tracks for this request.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+PATH: Epic Initialization — please produce tracks
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please generate the implementation tickets for this track.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please read test.txt
+You are assigned to Ticket T1.
+Task Description: do something
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+role: tool
+Here are the results: {"content": "done"}
+------------------
+--- MOCK INVOKED ---
+ARGS: ['C:\\projects\\manual_slop\\tests\\mock_gemini_cli.py', '-m', 'gemini-2.5-flash-lite', '--prompt', '', '--output-format', 'stream-json']
+PROMPT:
+You are a helpful coding assistant with access to a PowerShell tool (run_powershell) and MCP tools (file access: read_file, list_directory, search_files, get_file_summary, web access: web_search, fetch_url). When calling file/directory tools, always use the 'path' parameter for the target path. When asked to create or edit files, prefer targeted edits over full rewrites. Always explain what you are doing before invoking the tool.
+
+When writing or rewriting large files (especially those containing quotes, backticks, or special characters), avoid python -c with inline strings. Instead: (1) write a .py helper script to disk using a PS here-string (@'...'@ for literal content), (2) run it with `python <script>`, (3) delete the helper. For small targeted edits, use PowerShell's (Get-Content) / .Replace() / Set-Content or Add-Content directly.
+
+When making function calls using tools that accept array or object parameters ensure those are structured using JSON. For example:
+When you need to verify a change, rely on the exit code and stdout/stderr from the tool — the user's context files are automatically refreshed after every tool call, so you do NOT need to re-read files that are already provided in the <context> block.
+
+[USER SYSTEM PROMPT]
+
+You are the Tier 1 Orchestrator (Product Manager) for the Manual Slop project.
+Your role is high-level strategic planning, architecture enforcement, and cross-module delegation.
+You operate strictly on metadata, summaries, and executive-level directives.
+NEVER request or attempt to read raw implementation code unless specifically provided in a Macro-Diff.
+Maintain a "Godot ECS Flat List format" (JSON array of objects) for structural outputs.
+
+PATH: Epic Initialization (Project Planning)
+GOAL: Break down a massive feature request into discrete Implementation Tracks.
+
+CONSTRAINTS:
+- IGNORE all source code, AST skeletons, and previous micro-task histories.
+- FOCUS ONLY on the Repository Map and Project Meta-State.
+
+OUTPUT REQUIREMENT:
+Return a JSON array of 'Tracks'. Each track object must follow the Godot ECS Flat List format:
+[
+  {
+    "id": "track_unique_id",
+    "type": "Track",
+    "module": "target_module_name",
+    "persona": "required_tech_lead_persona",
+    "severity": "Low|Medium|High",
+    "goal": "Descriptive goal",
+    "acceptance_criteria": ["criteria_1", "criteria_2"]
+  },
+  ...
+]
+
+
+<context>
+
+</context>
+
+### USER REQUEST:
+Add timestamps
+
+### REPOSITORY MAP:
+
+
+### TRACK HISTORY:
+Track: api_hooks_verification_20260223
+Status: new
+Overview: This track focuses on integrating the existing, previously implemented API hooks (from track `test_hooks_20260223`) into the Conductor workflow. The primary goal is to automate the verification steps within the "Phase Completion Verification and Checkpointing Protocol", reducing the need for manual user intervention and enabling a more streamlined, automated development process.
+---
+Track: api_metrics_20260223
+Status: new
+Overview: This track aims to optimize token efficiency and transparency by reviewing and improving how vendor APIs (Gemini and Anthropic) handle conservative context pruning. The primary focus is on extracting, plotting, and exposing deep metrics to the GUI so developers can intuit how close they are to API limits (e.g., token caps, cache counts, history bleed).
+---
+Track: api_vendor_alignment_20260223
+Status: new
+Overview: This track involves a comprehensive audit of the "Manual Slop" codebase to ensure that the integration with Google Gemini (`google-genai`) and Anthropic Claude (`anthropic`) SDKs aligns perfectly with their latest official documentation and best practices. The goal is to identify discrepancies, performance bottlenecks, or deprecated patterns and implement the necessary fixes.
+---
+Track: architecture_boundary_hardening_20260302
+Status: new
+Overview: The `manual_slop` project sandbox provides AI meta-tooling (`mma_exec.py`, `tool_call.py`) to orchestrate its own development. When AI agents added advanced AST tools (like `set_file_slice`) to `mcp_client.py` for meta-tooling, they failed to fully integrate them into the application's GUI, config, or HITL (Human-In-The-Loop) safety models. Additionally, meta-tooling scripts are bleeding tokens and rely on non-portable hardcoded machine paths, while the internal application's state machine can deadlock.
+---
+Track: cache_analytics_20260306
+Status: planned
+Overview: Gemini cache hit/miss visualization, memory usage, TTL status display. Uses existing `ai_client.get_gemini_cache_stats()` which is implemented but has no GUI representation.
+---
+Track: codebase_migration_20260302
+Status: new
+Overview: This track focuses on restructuring the codebase to alleviate clutter by moving the main implementation files from the project root into a dedicated `src/` directory. Additionally, files that are completely unused by the current implementation will be automatically identified and removed. A new clean entry point (`sloppy.py`) will be created in the root directory.
+---
+Track: comprehensive_gui_ux_20260228
+Status: completed
+Overview: This track enhances the existing MMA orchestration GUI from its current functional-but-minimal state to a production-quality control surface. The existing implementation already has a working Track Browser, DAG tree visualizer, epic planning flow, approval dialogs, and token usage table. This track focuses on the **gaps**: dedicated tier stream panels, DAG editing, track-scoped discussions, conductor lifecycle GUI forms, cost tracking, and visual polish.
+---
+Track: conductor_workflow_improvements_20260302
+Status: new
+Overview: Recent Tier 2 track implementations have resulted in feature bleed, redundant code, unread state variables, and degradation of TDD discipline (e.g., zero-assertion tests).
+This track updates the Conductor documentation (`workflow.md`) and the Gemini skills for Tiers 2 and 3 to hard-enforce TDD, prevent hallucinated "mock" implementations, and enforce strict codebase auditing before writing code.
+---
+Track: consolidate_cruft_and_log_taxonomy_20260228
+Status: unknown
+Overview: This track focuses on cleaning up the project root by consolidating temporary and test-related files into a dedicated directory and establishing a structured taxonomy for session logs. This will improve project organization and make manual file exploration easier before a dedicated GUI log viewer is implemented.
+---
+Track: context_management_20260223
+Status: new
+Overview: This track implements UI improvements and structural changes to Manual Slop to provide explicit visualization of context memory usage and token consumption, fulfilling the "Expert systems level utility" and "Full control" product goals.
+---
+Track: context_token_viz_20260301
+Status: new
+Overview: product.md lists "Context & Memory Management" as primary use case #2: "Better visualization and management of token usage and context memory, allowing developers to optimize prompt limits manually." The backend already computes everything needed via `ai_client.get_history_bleed_stats()` (ai_client.py:1657-1796, 140 lines). This track builds the UI to expose it.
+---
+Track: cost_token_analytics_20260306
+Status: planned
+Overview: # Implementation Plan: Cost & Token Analytics Panel (cost_token_analytics_20260306)
+
+> **Reference:** [Spec](./spec.md) | [Architecture Guide](../../../docs/guide_architecture.md)
+
+## Phase 1: Foundat...
+---
+Track: deepseek_support_20260225
+Status: new
+Overview: Implement a new AI provider module to support the DeepSeek API within the Manual Slop application. This integration will leverage a dedicated SDK to provide access to high-performance models (DeepSeek-V3 and DeepSeek-R1) with support for streaming, tool calling, and detailed reasoning traces.
+---
+Track: deep_ast_context_pruning_20260306
+Status: planned
+Overview: Use tree_sitter to parse target file AST and inject condensed skeletons into worker prompts. Currently workers receive full file context; this track reduces token burn by injecting only relevant function/method signatures.
+---
+Track: documentation_refresh_20260224
+Status: new
+Overview: This track implements a high-density, expert-level documentation suite for the Manual Slop project. The documentation style is strictly modeled after the **pedagogical and narrative standards** of `gencpp` and `VEFontCache-Odin`. It moves beyond simple "User Guides" to provide a **"USA Graphics Company"** architectural reference: high information density, tactical technical transparency, and a narrative intent that guides a developer from high-level philosophy to low-level implementation.
+---
+Track: enhanced_context_control_20260307
+Status: planned
+Overview: Give developers granular control over how files are included in the AI context and provide visibility into the active Gemini cache state. This involves moving away from a simple list of files to a structured format with per-file flags (`auto_aggregate`, `force_full`), revamping the UI to display this state, and updating the context builders and API clients to respect and expose these details.
+---
+Track: event_driven_metrics_20260223
+Status: new
+Overview: Refactor the API metrics update mechanism to be event-driven. Currently, the UI likely polls or recalculates metrics on every frame. This track will implement a signal/event system where `ai_client.py` broadcasts updates only when significant API activities (requests, responses, tool calls, or stream chunks) occur.
+---
+Track: feature_bleed_cleanup_20260302
+Status: new
+Overview: Multiple tracks added code to `gui_2.py` without removing the old versions, leaving
+dead duplicate methods, conflicting menu bar designs, and redundant state initializations.
+This track removes confirmed dead code, resolves the two-menubar conflict, and cleans
+up the token budget layout regression — restoring a consistent, non-contradictory design state.
+---
+Track: gemini_cli_headless_20260224
+Status: new
+Overview: This track integrates the `gemini` CLI as a headless backend provider for Manual Slop. This allows users to leverage their Gemini subscription and the CLI's advanced features (e.g., specialized sub-agents like `codebase_investigator`, structured JSON streaming, and robust session management) directly within the Manual Slop GUI.
+---
+Track: gemini_cli_parity_20260225
+Status: new
+Overview: Achieve full functional and behavioral parity between the Gemini CLI integration (`gemini_cli_adapter.py`, `cli_tool_bridge.py`) and the direct Gemini API implementation (`ai_client.py`). This ensures that users leveraging the Gemini CLI as a headless backend provider experience the same level of capability, reliability, and observability as direct API users.
+---
+Track: gui2_feature_parity_20260223
+Status: new
+Overview: # Specification: GUIv2 Feature Parity
+
+## 1. Overview
+
+This track aims to bring `gui_2.py` (the `imgui-bundle` based UI) to feature parity with the existing `gui.py` (the `dearpygui` based UI). This i...
+---
+Track: gui2_parity_20260224
+Status: new
+Overview: The project is transitioning from `gui.py` (Dear PyGui-based) to `gui_2.py` (ImGui Bundle-based) to leverage advanced multi-viewport and docking features not natively supported by Dear PyGui. This track focuses on achieving full visual, functional, and performance parity between the two implementations, ultimately enabling the decommissioning of the original `gui.py`.
+---
+Track: gui_decoupling_controller_20260302
+Status: new
+Overview: `gui_2.py` currently operates as a Monolithic God Object (3,500+ lines). It violates the Data-Oriented Design heuristic by owning complex business logic, orchestrator hooks, and markdown file building. This track extracts the core state machine and lifecycle into a headless `app_controller.py`, turning the GUI into a pure immediate-mode view.
+---
+Track: gui_layout_refinement_20260223
+Status: new
+Overview: This track focuses on a holistic review and reorganization of the Manual Slop GUI. The goal is to ensure that AI tunings, diagnostic features, context management, and discussion history are logically placed to support an expert-level "Multi-Viewport" workflow. We will strengthen the "Arcade Aesthetics" and "Tactile Density" values while ensuring the layout remains intuitive for power users.
+---
+Track: gui_performance_20260223
+Status: new
+Overview: This track focuses on identifying and resolving severe frametime performance issues in the Manual Slop GUI. Current observations indicate massive frametime bloat even on idle startup, with performance significantly regressing (target 60 FPS / <16.6ms) since commit `8aa70e287fbf93e669276f9757965d5a56e89b10`.
+---
+Track: gui_performance_profiling_20260307
+Status: unknown
+Overview: Implement fine-grained performance profiling within the main ImGui rendering loop (`gui_2.py`) to ensure adherence to data-oriented and immediate mode heuristics. This track will provide visual diagnostics for high-overhead UI components, allowing developers to monitor and optimize render frame times.
+---
+Track: gui_sim_extension_20260224
+Status: new
+Overview: This track aims to expand the test simulation suite by introducing comprehensive, in-breadth tests that cover all facets of the GUI interaction. The original small test simulation will be preserved as a useful baseline. The new extended tests will be structured as multiple focused, modular scripts rather than a single long-running journey, ensuring maintainability and targeted coverage.
+---
+Track: history_segregation_20260224
+Status: new
+Overview: Currently, `manual_slop.toml` stores both project configuration and the entire discussion history. This leads to redundancy and potential context bloat if the AI agent reads the raw TOML file via its tools. This track will move the discussion history to a dedicated sibling TOML file (`history.toml`) and strictly blacklist it from the AI agent's file tools to ensure it only interacts with the curated context provided in the prompt.
+---
+Track: kill_abort_workers_20260306
+Status: planned
+Overview: Add ability to kill/abort a running Tier 3 worker mid-execution. Currently workers run to completion; add cancel button with forced termination option.
+---
+Track: live_gui_testing_20260223
+Status: new
+Overview: Update the testing suite to ensure all tests (especially GUI-related and integration tests) communicate with a live running instance of `gui.py` started with the `--enable-test-hooks` argument. This ensures that tests can verify the actual application state and metrics via the built-in API hooks.
+---
+Track: live_ux_test_20260223
+Status: new
+Overview: This track implements a robust, "human-like" interaction test suite for Manual Slop. The suite will simulate a real user's workflow—from project creation to complex AI discussions and history management—using the application's API hooks. It aims to verify the "Integrated Workspace" functionality, tool execution, and history persistence without requiring manual human input, while remaining slow enough for visual audit.
+---
+Track: logging_refactor_20260226
+Status: new
+Overview: Currently, `gui_2.py` and the test suites generate a large number of log files in a flat `logs/` directory. These logs accumulate quickly, especially during incremental development and testing. This track aims to organize logs into session-based sub-directories and implement a heuristic-based pruning system to keep the log directory clean while preserving valuable sessions.
+---
+Track: manual_block_control_20260306
+Status: planned
+Overview: Allow user to manually block or unblock tickets with custom reasons. Currently blocked tickets rely solely on dependency resolution; add manual override capability.
+---
+Track: manual_skeleton_injection_20260306
+Status: planned
+Overview: Add UI controls to manually inject file skeletons into discussions. Allow user to preview skeleton content before sending to AI, with option to toggle between skeleton and full file.
+---
+Track: manual_slop_headless_20260225
+Status: new
+Overview: Transform Manual Slop into a decoupled, container-friendly backend service. This track enables the core AI orchestration and tool execution logic to run without a GUI, exposing its capabilities via a secured REST API optimized for an Unraid Docker environment.
+---
+Track: minimax_provider_20260306
+Status: unknown
+Overview: Add MiniMax as a new AI provider to Manual Slop. MiniMax provides high-performance text generation models (M2.5, M2.1, M2) with massive context windows (200k+ tokens) and competitive pricing.
+---
+Track: mma_agent_focus_ux_20260302
+Status: new
+Overview: All MMA observability panels (comms history, tool calls, discussion) display
+global/session-scoped data. When 4 tiers are running concurrently, their traffic
+is indistinguishable. This track adds a `source_tier` field to every comms and
+tool log entry at the point of emission, then adds a "Focus Agent" selector that
+filters the Operations Hub panels to show only one tier's traffic at a time.
+
+**Depends on:** `feature_bleed_cleanup_20260302` (Phase 1 removes the dead comms
+panel duplicate; this track extends the live panel at gui_2.py:~3400).
+---
+Track: MMA Core Engine Implementation
+Status: planning
+Overview: # Specification: MMA Core Engine Implementation
+
+## 1. Overview
+This track consolidates the implementation of the 4-Tier Hierarchical Multi-Model Architecture into the `manual_slop` codebase. The arch...
+---
+Track: MMA Dashboard Visualization Overhaul
+Status: planned
+Overview: Make the invisible backend operations visible and interactive. The current GUI is too barebones to effectively manage a multi-agent system. This track overhauls the MMA Dashboard to provide real-time insights into tracks, task dependencies, and agent streams.
+---
+Track: MMA Data Architecture & DAG Engine
+Status: planned
+Overview: Restructure how `manual_slop` stores and executes work. The current implementation relies on global state and linear execution, which does not support the complexity of multi-agent, task-based workflows. This track establishes a robust, data-oriented foundation using track-scoped state and a native Python Directed Acyclic Graph (DAG) engine.
+---
+Track: mma_formalization_20260225
+Status: new
+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.
+---
+Track: mma_implementation_20260224
+Status: new
+Overview: # Specification: 4-Tier Architecture Implementation & Conductor Self-Improvement
+
+## 1. Overview
+This track encompasses two major phases. Phase 1 focuses on designing a comprehensive, step-by-step imp...
+---
+Track: mma_multiworker_viz_20260306
+Status: planned
+Overview: Split-view GUI for parallel worker streams per tier. Visualize multiple concurrent workers with individual status, output tabs, and resource usage. Enable kill/restart per worker.
+---
+Track: MMA Orchestrator Integration
+Status: in-progress
+Overview: Implement the full hierarchical orchestration loop, connecting Tier 1 (PM) strategic planning with Tier 2 (Tech Lead) tactical ticket generation. This track will enable the GUI to autonomously break down high-level user 'Epics' into actionable tracks and tickets, and manage their execution through the multi-agent system.
+---
+Track: mma_pipeline_fix_20260301
+Status: new
+Overview: The MMA pipeline has a verified code path from `run_worker_lifecycle` → `_queue_put("response", ...)` → `_process_event_queue` → `_pending_gui_tasks("handle_ai_response")` → `mma_streams[stream_id] = text`. However, the robust_live_simulation track's session compression (2026-02-28) documented that Tier 3 worker output never appears in `mma_streams` during actual GUI operation. The simulation only ever sees `'Tier 1'` in `mma_streams` keys.
+
+This track diagnoses and fixes the pipeline break, then verifies end-to-end that worker output flows from `ai_client.send()` through to the GUI's `mma_streams` dict.
+---
+Track: mma_utilization_refinement_20260226
+Status: new
+Overview: Refine the Multi-Model Architecture (MMA) implementation within the Conductor framework to ensure clear role segregation, proper tool permissions, and improved observability for sub-agents.
+---
+Track: mma_verification_20260225
+Status: new
+Overview: This track aims to review and verify the implementation of the 4-Tier Hierarchical Multi-Model Architecture (MMA) within the Conductor framework. It will confirm that Conductor operates as a Tier 2 Tech Lead/Orchestrator and can successfully delegate tasks to Tier 3 (Workers) and Tier 4 (QA/Utility) sub-agents. A key part of this track is investigating whether this hierarchy should be enforced via a single centralized skill or through separate role-based sub-agent definitions.
+---
+Track: mma_verification_mock
+Status: new
+Overview: This is a mock track designed to verify the full Tier 2 -> Tier 3 -> Tier 4 delegation flow within the Conductor framework.
+---
+Track: native_orchestrator_20260306
+Status: planned
+Overview: Absorb `mma_exec.py` functionality into core application. Manual Slop natively reads/writes plan.md, manages metadata.json, and orchestrates MMA tiers in pure Python without external CLI subprocess calls.
+---
+Track: on_demand_def_lookup_20260306
+Status: planned
+Overview: Add ability for agent to request specific class/function definitions during discussion. Parse @symbol syntax to trigger lookup and display inline in the discussion.
+---
+Track: per_ticket_model_20260306
+Status: planned
+Overview: Allow user to manually select which model to use for a specific ticket, overriding the default tier model. Useful for forcing smarter model on hard tickets.
+---
+Track: pipeline_pause_resume_20260306
+Status: planned
+Overview: Add global pause/resume for entire DAG execution pipeline. Allow user to freeze all worker activity and resume later without losing state.
+---
+Track: python_style_refactor_20260227
+Status: unknown
+Overview: # Specification: AI-Optimized Python Style Refactor
+
+## 1. Overview
+Refactor the Python codebase to a "Single-Space, Ultra-Compact" style specifically designed to minimize token consumption for AI age...
+---
+Track: Robust Live Simulation Verification
+Status: planned
+Overview: Establish a robust, visual simulation framework to prevent regressions in the complex GUI and asynchronous orchestration layers. This track replaces manual human verification with an automated script that clicks through the GUI and verifies the rendered state.
+---
+Track: session_insights_20260306
+Status: planned
+Overview: Token usage over time, cost projections, session summary with efficiency scores. Visualize session_logger data.
+---
+Track: simulation_hardening_20260301
+Status: new
+Overview: The `robust_live_simulation_verification` track is marked complete but its session compression documents three unresolved issues: (1) brittle mock that triggers the wrong approval popup, (2) popup state desynchronization after "Accept" clicks, (3) Tier 3 output never appearing in `mma_streams` (fixed by `mma_pipeline_fix` track). This track stabilizes the simulation framework so it reliably passes end-to-end.
+---
+Track: strict_execution_queue_completed_20260306
+Status: completed
+Overview: No overview available.
+---
+Track: strict_static_analysis_and_typing_20260302
+Status: new
+Overview: The codebase currently suffers from massive type-safety debt (512+ `mypy` errors across 64 files) and lingering `ruff` violations. This track will harden the foundation by resolving all violations, enforcing strict typing (especially in `gui_2.py` and `api_hook_client.py`), and integrating pre-commit checks. This is a prerequisite for safe AI-driven refactoring.
+---
+Track: tech_debt_and_test_cleanup_20260302
+Status: new
+Overview: Due to rapid iterative development and feature bleed across multiple Tier 2-led tracks, significant tech debt has accumulated in both the testing suite and `gui_2.py`.
+This track will clean up test fixtures, enforce test assertion integrity, and remove dead codebase remnants.
+---
+Track: test_architecture_integrity_audit_20260304
+Status: unknown
+Overview: Comprehensive audit of testing infrastructure and simulation framework to identify false positive risks, coverage gaps, and simulation fidelity issues. This analysis was triggered by a request to review how tests and simulations are setup, whether tests can report passing grades when they fail, and if simulations are rigorous enough or are just rough emulators.
+---
+Track: test_curation_20260225
+Status: new
+Overview: The current test suite for **Manual Slop** and the **Conductor** framework has grown incrementally and lacks a formal organization. This track aims to curate, categorize, and organize existing tests, specifically blacklisting Conductor-specific (MMA) tests from manual_slop's test runs. We will use a central manifest for test management and perform an exhaustive review of all tests to eliminate redundancy.
+---
+Track: test_hooks_20260223
+Status: new
+Overview: This track introduces a comprehensive suite of API hooks designed specifically for the Gemini CLI and the Conductor framework. These hooks will allow automated agents to manipulate and test the internal state of the application without requiring manual GUI interaction, enabling automated test-driven development and track progression validation.
+---
+Track: Test Integrity Audit & Intent Documentation
+Status: in_progress
+Overview: Audit and fix tests that have been "simplified" or "dumbed down" by AI agents, restoring their original verification intent through explicit documentation comments. This track addresses the growing problem of AI agents "completing" tasks by weakening test assertions rather than implementing proper functionality.
+---
+Track: test_regression_verification_20260307
+Status: unknown
+Overview: Verify that all existing tests pass with 0 regressions after recent track implementations (Kill/Abort, Block/Unblock, Pause/Resume, Per-Ticket Model Override).
+---
+Track: test_stabilization_20260302
+Status: new
+Overview: The goal of this track is to stabilize and unify the project's test suite. This involves resolving pervasive `asyncio` lifecycle errors, consolidating redundant testing paradigms (specifically manual GUI subprocesses), ensuring artifact isolation in `./tests/artifacts/`, implementing functional assertions for currently mocked-out tests, and updating documentation to reflect the finalized verification framework.
+---
+Track: ticket_queue_mgmt_20260306
+Status: planned
+Overview: Allow user to manually reorder, prioritize, or requeue tickets in the DAG. Add drag-drop reordering, priority tags, and bulk selection for execute/skip/block operations.
+---
+Track: tier4_auto_patching_20260306
+Status: planned
+Overview: Elevate Tier 4 from log summarizer to auto-patcher. When verification tests fail, Tier 4 generates a unified diff patch. GUI displays side-by-side diff; user clicks Apply Patch to resume pipeline.
+---
+Track: Tiered Context Scoping & HITL Approval
+Status: planned
+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.
+---
+Track: tool_usage_analytics_20260306
+Status: planned
+Overview: Analytics panel showing most-used tools, average execution time, and failure rates. Uses existing tool execution data from ai_client.
+---
+Track: track_progress_viz_20260306
+Status: planned
+Overview: Progress bars and percentage completion for active tracks and tickets. Better visualization of DAG execution state.
+---
+Track: true_parallel_worker_execution_20260306
+Status: planned
+Overview: Add worker pool management and configurable concurrency limits to the DAG engine. Currently workers execute in parallel per tick but with no limits or tracking; this track adds max_workers configuration, worker tracking, and proper pool management.
+---
+Track: ui_performance_20260223
+Status: new
+Overview: This track aims to resolve subpar UI performance (currently perceived below 60 FPS) by implementing a robust performance monitoring system. This system will collect high-resolution telemetry (Frame Time, Input Lag, Thread Usage) and expose it to both the user (via a Diagnostics Panel) and the AI (via API hooks). This ensures that performance degradation is caught early during development and testing.
+---
+Track: visual_dag_ticket_editing_20260306
+Status: planned
+Overview: Replace linear ticket list with interactive node graph using ImGui Bundle node editor. Users can visually drag dependency lines, split nodes, or delete tasks before execution.
+---
+Track: caching_optimization_20260308
+Status: new
+Overview: This track aims to verify and optimize the caching strategies across all supported AI providers (Gemini, Anthropic, DeepSeek, MiniMax, and OpenAI). The goal is to minimize token consumption and latency by ensuring that static and recurring context (system prompts, tool definitions, project documents, and conversation history) are effectively cached using each provider's specific mechanisms.
+---
+Track: codebase_audit_20260308
+Status: new
+Overview: The objective of this track is to audit the `./src` and `./simulation` directories to improve human readability and maintainability. The codebase has matured, and it is necessary to identify and address redundant code paths and state tracking, add missing docstrings to critical paths, and organize declarations/definitions within files.
+---
+Track: conductor_path_configurable_20260306
+Status: unknown
+Overview: Eliminate all hardcoded paths in the application. Make directory paths configurable via `config.toml` or environment variables, allowing the running app to use different directories from development setup. This is **Phase 0 - Critical Infrastructure** that must be completed before other Phase 3 tracks.
+---
+Track: external_editor_integration_20260308
+Status: new
+Overview: This feature adds the ability to open files modified by AI agents in external text editors (such as VSCode or 10xNotepad) directly from the tool approval popup. This allows users to leverage their preferred editor's native diffing and editing capabilities before confirming an agent's changes.
+---
+Track: external_mcp_support_20260308
+Status: new
+Overview: This feature adds support for integrating external Model Context Protocol (MCP) servers into Manual Slop. This allows agents to utilize tools from a wide ecosystem of MCP servers (like those for databases, APIs, or specialized utilities) alongside the application's native tools.
+---
+Track: Bootstrap gencpp Python Bindings Project
+Status: pending
+Overview: Create a new standalone Python project to build CFFI bindings for gencpp (C/C++ staged metaprogramming library). This will eventually provide richer C++ AST understanding than tree-sitter (full type information, operators, specifiers) but is a longer-term effort. This track bootstraps the project structure and initial bindings.
+---
+Track: GUI Path Configuration in Context Hub
+Status: pending
+Overview: Add path configuration UI to the Context Hub in the GUI. Allow users to view and edit configurable paths (conductor, logs, scripts) directly from the application without manually editing config.toml or environment variables.
+---
+Track: hook_api_expansion_20260308
+Status: new
+Overview: This track aims to transform the Manual Slop Hook API into a comprehensive control plane for headless use. It focuses on exposing all relevant internal states (worker traces, AST metadata, financial metrics, concurrency telemetry) and providing granular control over the application's lifecycle, MMA pipeline, and context management. Additionally, it introduces a WebSocket-based streaming interface for real-time event delivery.
+---
+Track: log_session_overhaul_20260308
+Status: new
+Overview: This track focuses on centralizing log management, improving the reliability and scope of session restoration, and optimizing log storage by offloading large data blobs (scripts and tool outputs) to external files. It also aims to "clean" the discussion history by moving transient system warnings to a dedicated diagnostic log.
+---
+Track: manual_ux_validation_20260302
+Status: new
+Overview: This track is an unusual, highly interactive human-in-the-loop review session. The user will act as the primary QA and Designer, manually using the GUI and observing it during slow-interval simulation runs. The goal is to aggressively iterate on the "feel" of the application: analyzing blinking animations, structural decisions (Tabs vs. Panels vs. Collapsing Headers), knob/control placements, and the efficacy of popups (including adding auto-close timers).
+---
+Track: markdown_highlighting_20260308
+Status: new
+Overview: This track introduces rich text rendering to the Manual Slop GUI by adding support for GitHub-Flavored Markdown (GFM) in message and response views. It also adds syntax highlighting for code blocks and text content when the language context can be cheaply resolved (e.g., via known metadata or file extensions).
+---
+Track: openai_integration_20260308
+Status: new
+Overview: This track introduces support for OpenAI as a first-class model provider. It involves implementing a dedicated client in `src/ai_client.py`, updating configuration models, enhancing the GUI for provider selection, and integrating OpenAI into the tiered MMA architecture.
+---
+Track: Project-Specific Conductor Directory
+Status: pending
+Overview: Make the conductor directory per-project instead of global. Each project TOML can specify its own `conductor_dir` path, allowing separate track/state management per project. This enables using Manual Slop with multiple independent projects without track/ticket cross-pollution.
+---
+Track: rag_support_20260308
+Status: new
+Overview: This track introduces Retrieval-Augmented Generation (RAG) capabilities to Manual Slop. It allows agents to search and retrieve relevant information from large local codebases, project documentation, or external knowledge bases, overcoming context window limitations and reducing hallucination.
+---
+Track: saved_presets_20260308
+Status: new
+Overview: This feature introduces the ability to save, manage, and switch between system prompt presets for both global (application-wide) and project-specific contexts. Presets will include not only the system prompt text but also model-specific parameters like temperature and top_p, effectively allowing for "AI Profiles."
+---
+Track: saved_tool_presets_20260308
+Status: new
+Overview: This feature adds the ability to create, save, and manage "Tool Presets" for agent roles. These presets define which tools are available to an agent and their respective "auto" vs "ask" approval levels. Tools will be organized into dynamic, TOML-defined categories (e.g., Python, General) and integrated into the global and project-specific AI settings.
+---
+Track: selectable_ui_text_20260308
+Status: new
+Overview: This track aims to address UI inconveniences by making critical text across the GUI selectable and copyable. This includes discussion history, communication logs, tool outputs, and key metrics. The goal is to provide a standard "Copy to Clipboard" capability via OS-native selection and shortcuts (Ctrl+C).
+---
+Track: tool_bias_tuning_20260308
+Status: new
+Overview: This track introduces a mechanism to influence AI agent tool selection by implementing a weighting and scoring system at the orchestration layer. Since model APIs do not natively support tool priority, this feature uses semantic nudging (tags in tool descriptions) and explicit system instructions to "bias" the agent toward preferred tools and parameters.
+---
+Track: Tree-Sitter C/C++ MCP Tools
+Status: pending
+Overview: Add tree-sitter-based C and C++ parsing support to the MCP client, providing skeleton and outline tools for C/C++ codebases. Tools will be prefixed `ts_c_` and `ts_cpp_` to distinguish from existing Python tools and leave namespace open for future gencpp integration.
+---
+Track: ui_theme_overhaul_20260308
+Status: new
+Overview: This track aims to modernize the application's appearance by implementing a professional, high-fidelity UI theme using `imgui-bundle`'s native styling and theming capabilities. It focuses on improving typography, visual shapes, and introducing advanced features like custom shaders, multi-viewport support, and user-managed layout presets.
+---
+Track: ux_sim_test_20260308
+Status: unknown
+Overview: No overview available.
+---
+Track: zhipu_integration_20260308
+Status: new
+Overview: This track introduces support for Zhipu AI (z.ai) as a first-class model provider. It involves implementing a dedicated client in `src/ai_client.py` for the GLM series of models, updating configuration models, enhancing the GUI for provider selection, and integrating the provider into the tiered MMA architecture.
+---
+
+Please generate the implementation tracks for this request.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+PATH: Epic Initialization — please produce tracks
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please generate the implementation tickets for this track.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please read test.txt
+You are assigned to Ticket T1.
+Task Description: do something
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+role: tool
+Here are the results: {"content": "done"}
+------------------
diff --git a/src/app_controller.py b/src/app_controller.py
index 288fc28..243f3ef 100644
--- a/src/app_controller.py
+++ b/src/app_controller.py
@@ -346,40 +346,40 @@ class AppController:
   }
   self._gettable_fields = dict(self._settable_fields)
   self._gettable_fields.update({
-    'ui_focus_agent': 'ui_focus_agent',
-    'active_discussion': 'active_discussion',
-    '_track_discussion_active': '_track_discussion_active',
-    'proposed_tracks': 'proposed_tracks',
-    'mma_streams': 'mma_streams',
-    '_worker_status': '_worker_status',
-    'active_track': 'active_track',
-    'active_tickets': 'active_tickets',
-    'tracks': 'tracks',
-    'thinking_indicator': 'thinking_indicator',
-    'operations_live_indicator': 'operations_live_indicator',
-    'prior_session_indicator': 'prior_session_indicator',
-    '_show_patch_modal': '_show_patch_modal',
-    '_pending_patch_text': '_pending_patch_text',
-    '_pending_patch_files': '_pending_patch_files',
-    '_inject_file_path': '_inject_file_path',
-    '_inject_mode': '_inject_mode',
-    '_inject_preview': '_inject_preview',
-    '_show_inject_modal': '_show_inject_modal',
-    'bg_shader_enabled': 'bg_shader_enabled',
-    'global_system_prompt': 'ui_global_system_prompt',
-    'project_system_prompt': 'ui_project_system_prompt',
-    'global_preset_name': 'ui_global_preset_name',
-    'project_preset_name': 'ui_project_preset_name',
-    'temperature': 'temperature',
-    'max_tokens': 'max_tokens',
-    'show_preset_manager_modal': 'show_preset_manager_modal',
-    '_editing_preset_name': '_editing_preset_name',
-    '_editing_preset_content': '_editing_preset_content',
-    '_editing_preset_temperature': '_editing_preset_temperature',
-    '_editing_preset_top_p': '_editing_preset_top_p',
-    '_editing_preset_max_output_tokens': '_editing_preset_max_output_tokens',
-    '_editing_preset_scope': '_editing_preset_scope'
-   })
+   'ui_focus_agent': 'ui_focus_agent',
+   'active_discussion': 'active_discussion',
+   '_track_discussion_active': '_track_discussion_active',
+   'proposed_tracks': 'proposed_tracks',
+   'mma_streams': 'mma_streams',
+   '_worker_status': '_worker_status',
+   'active_track': 'active_track',
+   'active_tickets': 'active_tickets',
+   'tracks': 'tracks',
+   'thinking_indicator': 'thinking_indicator',
+   'operations_live_indicator': 'operations_live_indicator',
+   'prior_session_indicator': 'prior_session_indicator',
+   '_show_patch_modal': '_show_patch_modal',
+   '_pending_patch_text': '_pending_patch_text',
+   '_pending_patch_files': '_pending_patch_files',
+   '_inject_file_path': '_inject_file_path',
+   '_inject_mode': '_inject_mode',
+   '_inject_preview': '_inject_preview',
+   '_show_inject_modal': '_show_inject_modal',
+   'bg_shader_enabled': 'bg_shader_enabled',
+   'global_system_prompt': 'ui_global_system_prompt',
+   'project_system_prompt': 'ui_project_system_prompt',
+   'global_preset_name': 'ui_global_preset_name',
+   'project_preset_name': 'ui_project_preset_name',
+   'temperature': 'temperature',
+   'max_tokens': 'max_tokens',
+   'show_preset_manager_modal': 'show_preset_manager_modal',
+   '_editing_preset_name': '_editing_preset_name',
+   '_editing_preset_content': '_editing_preset_content',
+   '_editing_preset_temperature': '_editing_preset_temperature',
+   '_editing_preset_top_p': '_editing_preset_top_p',
+   '_editing_preset_max_output_tokens': '_editing_preset_max_output_tokens',
+   '_editing_preset_scope': '_editing_preset_scope'
+  })
   self.perf_monitor = performance_monitor.get_monitor()
   self._perf_profiling_enabled = False
   self._init_actions()
@@ -455,6 +455,8 @@ class AppController:
    '_test_callback_func_write_to_file': self._test_callback_func_write_to_file,
    '_set_env_var': lambda k, v: os.environ.update({k: v}),
    '_apply_preset': self._apply_preset,
+   '_cb_save_preset': self._cb_save_preset,
+   '_cb_delete_preset': self._cb_delete_preset,
    '_switch_project': self._switch_project,
    '_refresh_from_project': self._refresh_from_project
   }
@@ -1790,6 +1792,21 @@ class AppController:
   if preset.max_output_tokens is not None:
    self.max_tokens = preset.max_output_tokens
 
+ def _cb_save_preset(self, name, content, temp, top_p, max_tok, scope):
+  preset = models.Preset(
+   name=name,
+   system_prompt=content,
+   temperature=temp,
+   top_p=top_p,
+   max_output_tokens=max_tok
+  )
+  self.preset_manager.save_preset(preset, scope)
+  self.presets = self.preset_manager.load_all()
+
+ def _cb_delete_preset(self, name, scope):
+  self.preset_manager.delete_preset(name, scope)
+  self.presets = self.preset_manager.load_all()
+
  def _cb_load_track(self, track_id: str) -> None:
   state = project_manager.load_track_state(track_id, self.ui_files_base_dir)
   if state:
diff --git a/src/gui_2.py b/src/gui_2.py
index cdc8c64..7db9a49 100644
--- a/src/gui_2.py
+++ b/src/gui_2.py
@@ -889,6 +889,9 @@ class App:
    imgui.end_child()
    imgui.same_line()
    imgui.begin_child("preset_edit_area", imgui.ImVec2(500, 600), False)
+   p_name = self._editing_preset_name or "(New Preset)"
+   imgui.text_colored(C_IN, f"Editing Preset: {p_name}")
+   imgui.separator()
    imgui.text("Name:")
    _, self._editing_preset_name = imgui.input_text("##edit_name", self._editing_preset_name)
    imgui.text("Scope:")
@@ -909,27 +912,27 @@ class App:
 
    if imgui.button("Save", imgui.ImVec2(120, 0)):
     if self._editing_preset_name.strip():
-     new_p = models.Preset(
-      name=self._editing_preset_name.strip(), 
-      system_prompt=self._editing_preset_content,
-      temperature=self._editing_preset_temperature,
-      top_p=self._editing_preset_top_p,
-      max_output_tokens=self._editing_preset_max_output_tokens
+     self.controller._cb_save_preset(
+      self._editing_preset_name.strip(),
+      self._editing_preset_content,
+      self._editing_preset_temperature,
+      self._editing_preset_top_p,
+      self._editing_preset_max_output_tokens,
+      self._editing_preset_scope
      )
-     self.controller.preset_manager.save_preset(new_p, self._editing_preset_scope)
-     self.controller.presets = self.controller.preset_manager.load_all()
-     self.ai_status = f"Preset '{new_p.name}' saved to {self._editing_preset_scope}"
+     self.ai_status = f"Preset '{self._editing_preset_name.strip()}' saved to {self._editing_preset_scope}"
+   imgui.set_item_tooltip("Save the current preset settings")
    imgui.same_line()
    if imgui.button("Delete", imgui.ImVec2(120, 0)):
     if self._editing_preset_name.strip():
      try:
-      self.controller.preset_manager.delete_preset(self._editing_preset_name.strip(), self._editing_preset_scope)
-      self.controller.presets = self.controller.preset_manager.load_all()
+      self.controller._cb_delete_preset(self._editing_preset_name.strip(), self._editing_preset_scope)
       self.ai_status = f"Preset '{self._editing_preset_name}' deleted from {self._editing_preset_scope}"
       self._editing_preset_name = ""
       self._editing_preset_content = ""
      except Exception as e:
       self.ai_status = f"Error deleting: {e}"
+   imgui.set_item_tooltip("Delete the selected preset")
    imgui.same_line()
    if imgui.button("Close", imgui.ImVec2(120, 0)):
     self.show_preset_manager_modal = False
@@ -2925,9 +2928,10 @@ def hello():
     if is_sel:
      imgui.set_item_default_focus()
    imgui.end_combo()
-  imgui.same_line()
+  imgui.same_line(0, 8)
   if imgui.button("Manage Presets##global"):
    self.show_preset_manager_modal = True
+  imgui.set_item_tooltip("Open preset management modal")
   ch, self.ui_global_system_prompt = imgui.input_text_multiline("##gsp", self.ui_global_system_prompt, imgui.ImVec2(-1, 100))
   imgui.separator()
   imgui.text("Project System Prompt")
@@ -2941,11 +2945,11 @@ def hello():
     if is_sel:
      imgui.set_item_default_focus()
    imgui.end_combo()
-  imgui.same_line()
+  imgui.same_line(0, 8)
   if imgui.button("Manage Presets##project"):
    self.show_preset_manager_modal = True
+  imgui.set_item_tooltip("Open preset management modal")
   ch, self.ui_project_system_prompt = imgui.input_text_multiline("##psp", self.ui_project_system_prompt, imgui.ImVec2(-1, 100))
-
  def _render_theme_panel(self) -> None:
   if self.perf_profiling_enabled: self.perf_monitor.start_component("_render_theme_panel")
   exp, opened = imgui.begin("Theme", self.show_windows["Theme"])
diff --git a/src/presets.py b/src/presets.py
index 2b4a030..ad71db0 100644
--- a/src/presets.py
+++ b/src/presets.py
@@ -1,3 +1,4 @@
+import sys
 import tomllib
 import tomli_w
 from pathlib import Path
@@ -21,24 +22,21 @@ class PresetManager:
   presets: Dict[str, Preset] = {}
 
   # Load global presets
-  if self.global_path.exists():
+  data_global = self._load_file(self.global_path)
+  for name, p_data in data_global.get("presets", {}).items():
    try:
-    with open(self.global_path, "rb") as f:
-     data = tomllib.load(f)
-     for name, p_data in data.get("presets", {}).items():
-      presets[name] = Preset.from_dict(name, p_data)
-   except Exception:
-    pass
+    presets[name] = Preset.from_dict(name, p_data)
+   except Exception as e:
+    print(f"Error parsing global preset '{name}': {e}", file=sys.stderr)
 
   # Load project presets (overwriting global ones if names conflict)
-  if self.project_path and self.project_path.exists():
-   try:
-    with open(self.project_path, "rb") as f:
-     data = tomllib.load(f)
-     for name, p_data in data.get("presets", {}).items():
-      presets[name] = Preset.from_dict(name, p_data)
-   except Exception:
-    pass
+  if self.project_path:
+   data_project = self._load_file(self.project_path)
+   for name, p_data in data_project.get("presets", {}).items():
+    try:
+     presets[name] = Preset.from_dict(name, p_data)
+    except Exception as e:
+     print(f"Error parsing project preset '{name}': {e}", file=sys.stderr)
 
   return presets
 
@@ -75,8 +73,14 @@ class PresetManager:
    return {"presets": {}}
   try:
    with open(path, "rb") as f:
-    return tomllib.load(f)
-  except Exception:
+    data = tomllib.load(f)
+    if not isinstance(data, dict):
+     return {"presets": {}}
+    if "presets" not in data:
+     data["presets"] = {}
+    return data
+  except Exception as e:
+   print(f"Error loading presets from {path}: {e}", file=sys.stderr)
    return {"presets": {}}
 
  def _save_file(self, path: Path, data: Dict[str, Any]) -> None:
diff --git a/tests/test_saved_presets_sim.py b/tests/test_saved_presets_sim.py
index 1934c28..0b20f41 100644
--- a/tests/test_saved_presets_sim.py
+++ b/tests/test_saved_presets_sim.py
@@ -3,9 +3,39 @@ import time
 import tomli_w
 import os
 import json
+import shutil
 from pathlib import Path
 from src.api_hook_client import ApiHookClient
 
+@pytest.fixture(scope="session", autouse=True)
+def test_env_setup():
+ temp_workspace = Path("tests/artifacts/live_gui_workspace")
+ if temp_workspace.exists():
+  try: shutil.rmtree(temp_workspace)
+  except: pass
+ temp_workspace.mkdir(parents=True, exist_ok=True)
+ 
+ config_path = temp_workspace / "config.toml"
+ manual_slop_path = temp_workspace / "manual_slop.toml"
+ 
+ # Create minimal project file
+ manual_slop_path.write_text("[project]\nname = 'TestProject'\n", encoding="utf-8")
+ 
+ # Create local config.toml
+ config_path.write_text(tomli_w.dumps({
+  "projects": {
+   "paths": [str(manual_slop_path.absolute())],
+   "active": str(manual_slop_path.absolute())
+  },
+  "ai": {
+   "provider": "gemini",
+   "model": "gemini-2.5-flash-lite"
+  }
+ }))
+ yield
+ # Cleanup handled by live_gui fixture usually, but we can be explicit
+ if config_path.exists(): config_path.unlink()
+
 def test_preset_switching(live_gui):
  client = ApiHookClient()
  
@@ -58,10 +88,6 @@ def test_preset_switching(live_gui):
   })
   time.sleep(2) # Wait for processing
   
-  # Verify where it thinks the project is
-  state = client.get_gui_state()
-  print(f"DEBUG: ui_files_base_dir={state.get('files_base_dir')}")
-  
   # Apply Global Preset (should use override from project if available in merged list)
   client.push_event("custom_callback", {
    "callback": "_apply_preset",
@@ -86,6 +112,7 @@ def test_preset_switching(live_gui):
   assert state["project_preset_name"] == "TestProject"
   assert state["project_system_prompt"] == "Project Prompt"
   assert state["temperature"] == 0.3
+  
   # Select "None"
   client.push_event("custom_callback", {
    "callback": "_apply_preset",
@@ -97,7 +124,45 @@ def test_preset_switching(live_gui):
   
   # Prompt remains from previous application
   assert state["global_system_prompt"] == "Overridden Prompt"
+
  finally:
   # Cleanup
   if global_presets_path.exists(): global_presets_path.unlink()
   if project_presets_path.exists(): project_presets_path.unlink()
+
+def test_preset_manager_modal(live_gui):
+ client = ApiHookClient()
+ temp_workspace = Path("tests/artifacts/live_gui_workspace")
+ global_presets_path = temp_workspace / "presets.toml"
+ project_presets_path = temp_workspace / "project_presets.toml"
+ 
+ # Open Modal
+ client.set_value("show_preset_manager_modal", True)
+ time.sleep(1)
+ 
+ # Create New Preset via Modal Logic (triggering the callback directly for reliability in headless)
+ client.push_event("custom_callback", {
+  "callback": "_cb_save_preset",
+  "args": ["ModalPreset", "Modal Content", 0.9, 1.0, 4096, "global"]
+ })
+ time.sleep(2)
+ 
+ # Verify file exists
+ assert global_presets_path.exists()
+ with open(global_presets_path, "rb") as f:
+  import tomllib
+  data = tomllib.load(f)
+  assert "ModalPreset" in data["presets"]
+  assert data["presets"]["ModalPreset"]["temperature"] == 0.9
+ 
+ # Delete Preset via Modal Logic
+ client.push_event("custom_callback", {
+  "callback": "_cb_delete_preset",
+  "args": ["ModalPreset", "global"]
+ })
+ time.sleep(2)
+ 
+ # Verify file content
+ with open(global_presets_path, "rb") as f:
+  data = tomllib.load(f)
+  assert "ModalPreset" not in data["presets"]