conductor(tracks): Add two deferred future tracks

- aggregation_smarter_summaries: Sub-agent summarization, hash-based caching
- system_context_exposure: Expose hidden _SYSTEM_PROMPT for user customization

.opencode/agents/explore.md

@@ -1,7 +1,7 @@
----
+---
 description: Fast, read-only agent for exploring the codebase structure
 mode: subagent
-model: MiniMax-M2.5
+model: minimax-coding-plan/MiniMax-M2.7
 temperature: 0.2
 permission:
   edit: deny

.opencode/agents/general.md

@@ -1,7 +1,7 @@
----
+---
 description: General-purpose agent for researching complex questions and executing multi-step tasks
 mode: subagent
-model: MiniMax-M2.5
+model: minimax-coding-plan/MiniMax-M2.7
 temperature: 0.3
 ---
 

.opencode/agents/tier1-orchestrator.md

@@ -1,7 +1,7 @@
----
+---
 description: Tier 1 Orchestrator for product alignment, high-level planning, and track initialization
 mode: primary
-model: MiniMax-M2.5
+model: minimax-coding-plan/MiniMax-M2.7
 temperature: 0.5
 permission:
   edit: ask
@@ -18,7 +18,7 @@ ONLY output the requested text. No pleasantries.
 
 ## Context Management
 
-**MANUAL COMPACTION ONLY** — Never rely on automatic context summarization.
+**MANUAL COMPACTION ONLY** <EFBFBD> Never rely on automatic context summarization.
 Use `/compact` command explicitly when context needs reduction.
 Preserve full context during track planning and spec creation.
 
@@ -105,7 +105,7 @@ Use `manual-slop_py_get_code_outline`, `manual-slop_py_get_definition`,
 Document existing implementations with file:line references in a
 "Current State Audit" section in the spec.
 
-**FAILURE TO AUDIT = TRACK FAILURE** — Previous tracks failed because specs
+**FAILURE TO AUDIT = TRACK FAILURE** <EFBFBD> Previous tracks failed because specs
 asked to implement features that already existed.
 
 ### 2. Identify Gaps, Not Features

.opencode/agents/tier2-tech-lead.md

@@ -1,7 +1,7 @@
----
+---
 description: Tier 2 Tech Lead for architectural design and track execution with persistent memory
 mode: primary
-model: MiniMax-M2.5
+model: minimax-coding-plan/MiniMax-M2.7
 temperature: 0.4
 permission:
   edit: ask
@@ -14,9 +14,9 @@ ONLY output the requested text. No pleasantries.
 
 ## Context Management
 
-**MANUAL COMPACTION ONLY** — Never rely on automatic context summarization.
+**MANUAL COMPACTION ONLY** <EFBFBD> Never rely on automatic context summarization.
 Use `/compact` command explicitly when context needs reduction.
-You maintain PERSISTENT MEMORY throughout track execution — do NOT apply Context Amnesia to your own session.
+You maintain PERSISTENT MEMORY throughout track execution <EFBFBD> do NOT apply Context Amnesia to your own session.
 
 ## CRITICAL: MCP Tools Only (Native Tools Banned)
 
@@ -134,14 +134,14 @@ Before implementing:
 - Zero-assertion ban: Tests MUST have meaningful assertions
 - Delegate test creation to Tier 3 Worker via Task tool
 - Run tests and confirm they FAIL as expected
-- **CONFIRM FAILURE** — this is the Red phase
+- **CONFIRM FAILURE** <EFBFBD> this is the Red phase
 
 ### 3. Green Phase: Implement to Pass
 
 - **Pre-delegation checkpoint**: Stage current progress (`git add .`)
 - Delegate implementation to Tier 3 Worker via Task tool
 - Run tests and confirm they PASS
-- **CONFIRM PASS** — this is the Green phase
+- **CONFIRM PASS** <EFBFBD> this is the Green phase
 
 ### 4. Refactor Phase (Optional)
 

.opencode/agents/tier3-worker.md

@@ -1,7 +1,7 @@
----
+---
 description: Stateless Tier 3 Worker for surgical code implementation and TDD
 mode: subagent
-model: MiniMax-M2.5
+model: minimax-coding-plan/minimax-m2.7
 temperature: 0.3
 permission:
   edit: allow

.opencode/agents/tier4-qa.md

@@ -1,7 +1,7 @@
----
+---
 description: Stateless Tier 4 QA Agent for error analysis and diagnostics
 mode: subagent
-model: MiniMax-M2.5
+model: 	minimax-coding-plan/MiniMax-M2.7
 temperature: 0.2
 permission:
   edit: deny

conductor/product.md

@@ -17,7 +17,7 @@ For deep implementation details when planning or implementing tracks, consult `d
 ## Primary Use Cases
 
 - **Full Control over Vendor APIs:** Exposing detailed API metrics and configuring deep agent capabilities directly within the GUI.
-- **Context & Memory Management:** Better visualization and management of token usage and context memory. Includes granular per-file flags (**Auto-Aggregate**, **Force Full**) and a dedicated **'Context' role** for manual injections, allowing developers to optimize prompt limits with expert precision.
+- **Context & Memory Management:** Better visualization and management of token usage and context memory. Includes granular per-file flags (**Auto-Aggregate**, **Force Full**), a dedicated **'Context' role** for manual injections, and **Context Presets** for saving and loading named file/screenshot selections. Allows assigning specific context presets to MMA agent personas for granular cognitive load isolation.
 - **Manual "Vibe Coding" Assistant:** Serving as an auxiliary, multi-provider assistant that natively interacts with the codebase via sandboxed PowerShell scripts and MCP-like file tools, emphasizing manual developer oversight and explicit confirmation.
 
 ## Key Features
@@ -33,6 +33,7 @@ For deep implementation details when planning or implementing tracks, consult `d
     - **Track Browser:** Real-time visualization of all implementation tracks with status indicators and progress bars. Includes a dedicated **Active Track Summary** featuring a color-coded progress bar, precise ticket status breakdown (Completed, In Progress, Blocked, Todo), and dynamic **ETA estimation** based on historical completion times.
     - **Visual Task DAG:** An interactive, node-based visualizer for the active track's task dependencies using `imgui-node-editor`. Features color-coded state tracking (Ready, Running, Blocked, Done), drag-and-drop dependency creation, and right-click deletion.
     - **Strategy Visualization:** Dedicated real-time output streams for Tier 1 (Strategic Planning) and Tier 2/3 (Execution) agents, allowing the user to follow the agent's reasoning chains alongside the task DAG.
+    - **Agent-Focused Filtering:** Allows the user to focus the entire GUI (Session Hub, Discussion Hub, Comms) on a specific agent's activities and scoped context.
   - **Track-Scoped State Management:** Segregates discussion history and task progress into per-track state files. Supports **Project-Specific Conductor Directories**, defaulting to `./conductor` relative to each project's TOML file. Projects can define their own conductor path override in `manual_slop.toml` (`[conductor].dir`) via the Projects tab for isolated track management. This prevents global context pollution and ensures the Tech Lead session is isolated to the specific track's objective.
   **Native DAG Execution Engine:** Employs a Python-based Directed Acyclic Graph (DAG) engine to manage complex task dependencies. Supports automated topological sorting, robust cycle detection, and **transitive blocking propagation** (cascading `blocked` status to downstream dependents to prevent execution stalls).
 
@@ -54,7 +55,9 @@ For deep implementation details when planning or implementing tracks, consult `d
 - **High-Fidelity Selectable UI:** Most read-only labels and logs across the interface (including discussion history, comms payloads, tool outputs, and telemetry metrics) are now implemented as selectable text fields. This enables standard OS-level text selection and copying (Ctrl+C) while maintaining a high-density, non-editable aesthetic.
 - **High-Fidelity UI Rendering:** Employs advanced 3x font oversampling and sub-pixel positioning to ensure crisp, high-clarity text rendering across all resolutions, enhancing readability for dense logs and complex code fragments.
 - **Enhanced MMA Observability:** Worker streams and ticket previews now support direct text selection, allowing for easy extraction of specific logs or reasoning fragments during parallel execution.
-- **Detailed History Management:** Rich discussion history with branching, timestamping, and specific git commit linkage per conversation.
+- **Transparent Context Visibility:** A dedicated **Session Hub** exposes the exact aggregated markdown and resolved system prompt sent to the AI.
+- **Injection Timeline:** Discussion history visually indicates the precise moments when files or screenshots were injected into the session context.
+- **Detailed History Management:** Rich discussion history with non-linear timeline branching ("takes"), tabbed interface navigation, specific git commit linkage per conversation, and automated multi-take synthesis.
 - **Advanced Log Management:** Optimizes log storage by offloading large data (AI-generated scripts and tool outputs) to unique files within the session directory, using compact `[REF:filename]` pointers in JSON-L logs to minimize token overhead during analysis. Features a dedicated **Log Management panel** for monitoring, whitelisting, and pruning session logs.
 - **Full Session Restoration:** Allows users to load and reconstruct entire historical sessions from their log directories. Includes a dedicated, tinted **'Historical Replay' mode** that populates discussion history and provides a read-only view of prior agent activities.
 - **Dedicated Diagnostics Hub:** Consolidates real-time telemetry (FPS, CPU, Frame Time) and transient system warnings into a standalone **Diagnostics panel**, providing deep visibility into application health without polluting the discussion history.

conductor/tracks.md

@@ -1,4 +1,4 @@
-# Project Tracks
+# Project Tracks
 
 This file tracks all major tracks for the project. Each track has its own detailed plan in its respective folder.
 
@@ -35,9 +35,17 @@ This file tracks all major tracks for the project. Each track has its own detail
 7. [ ] **Track: Optimization pass for Data-Oriented Python heuristics**
     *Link: [./tracks/data_oriented_optimization_20260312/](./tracks/data_oriented_optimization_20260312/)*
 
-8. [ ] **Track: Rich Thinking Trace Handling**
+ 8. [x] **Track: Rich Thinking Trace Handling** - *Parse and display AI thinking/reasoning traces*
    *Link: [./tracks/thinking_trace_handling_20260313/](./tracks/thinking_trace_handling_20260313/)*
 
+ 9. [ ] **Track: Smarter Aggregation with Sub-Agent Summarization**
+    *Link: [./tracks/aggregation_smarter_summaries_20260322/](./tracks/aggregation_smarter_summaries_20260322/)*
+    *Goal: Sub-agent summarization during aggregation pass, hash-based caching for file summaries, smart outline generation for code vs text files.*
+
+ 10. [ ] **Track: System Context Exposure**
+     *Link: [./tracks/system_context_exposure_20260322/](./tracks/system_context_exposure_20260322/)*
+     *Goal: Expose hidden _SYSTEM_PROMPT from ai_client.py to users for customization via AI Settings.*
+
 ---
 
 ### GUI Overhauls & Visualizations
@@ -60,31 +68,32 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 5. [x] **Track: NERV UI Theme Integration** (Archived 2026-03-09)
 
-6. [ ] **Track: Custom Shader and Window Frame Support** 
+6. [X] **Track: Custom Shader and Window Frame Support** 
    *Link: [./tracks/custom_shaders_20260309/](./tracks/custom_shaders_20260309/)*
 
 7. [x] **Track: UI/UX Improvements - Presets and AI Settings**
    *Link: [./tracks/presets_ai_settings_ux_20260311/](./tracks/presets_ai_settings_ux_20260311/)*
    *Goal: Improve the layout, scaling, and control ergonomics of the Preset windows (Personas, Prompts, Tools) and AI Settings panel. Includes dual-control sliders and categorized tool management.*
 
-8. [ ] **Track: Session Context Snapshots & Visibility**
+8. [x] ~~**Track: Session Context Snapshots & Visibility**~~ (Archived 2026-03-22 - Replaced by discussion_hub_panel_reorganization)
    *Link: [./tracks/session_context_snapshots_20260311/](./tracks/session_context_snapshots_20260311/)*
    *Goal: Session-scoped context management, saving Context Presets, MMA assignment, and agent-focused session filtering in the UI.*
 
-9. [ ] **Track: Discussion Takes & Timeline Branching**
+9. [x] ~~**Track: Discussion Takes & Timeline Branching**~~ (Archived 2026-03-22 - Replaced by discussion_hub_panel_reorganization)
    *Link: [./tracks/discussion_takes_branching_20260311/](./tracks/discussion_takes_branching_20260311/)*
    *Goal: Non-linear discussion timelines via tabbed "takes", message branching, and synthesis generation workflows.*
 
+12. [ ] **Track: Discussion Hub Panel Reorganization**
+    *Link: [./tracks/discussion_hub_panel_reorganization_20260322/](./tracks/discussion_hub_panel_reorganization_20260322/)*
+    *Goal: Properly merge Session Hub into Discussion Hub (4 tabs: Discussion | Context Composition | Snapshot | Takes), establish Files & Media as project-level inventory, deprecate ui_summary_only, implement Context Composition and DAW-style Takes.*
+
 10. [ ] **Track: Undo/Redo History Support**
     *Link: [./tracks/undo_redo_history_20260311/](./tracks/undo_redo_history_20260311/)*
     *Goal: Robust, non-provider based undo/redo for text inputs, UI controls, discussion mutations, and context management. Includes hotkey support and a history list view.*
 
-11. [ ] **Track: Advanced Text Viewer with Syntax Highlighting**
+11. [x] **Track: Advanced Text Viewer with Syntax Highlighting**
     *Link: [./tracks/text_viewer_rich_rendering_20260313/](./tracks/text_viewer_rich_rendering_20260313/)*
 
-12. [ ] **Track: Frosted Glass Background Effect**
-    *Link: [./tracks/frosted_glass_20260313/](./tracks/frosted_glass_20260313/)*
-
 ---
 
 ### Additional Language Support
@@ -164,6 +173,10 @@ This file tracks all major tracks for the project. Each track has its own detail
 
 ### Completed / Archived
 
+-. [ ] ~~**Track: Frosted Glass Background Effect**~~ ***NOT WORTH THE PAIN***
+    *Link: [./tracks/frosted_glass_20260313/](./tracks/frosted_glass_20260313/)*
+
+
 - [x] **Track: External MCP Server Support** (Archived 2026-03-12)
 - [x] **Track: Project-Specific Conductor Directory** (Archived 2026-03-12)
 - [x] **Track: GUI Path Configuration in Context Hub** (Archived 2026-03-12)

conductor/tracks/aggregation_smarter_summaries_20260322/metadata.json

@@ -0,0 +1,17 @@
+{
+  "name": "aggregation_smarter_summaries",
+  "created": "2026-03-22",
+  "status": "future",
+  "priority": "medium",
+  "affected_files": [
+    "src/aggregate.py",
+    "src/file_cache.py",
+    "src/ai_client.py",
+    "src/models.py"
+  ],
+  "related_tracks": [
+    "discussion_hub_panel_reorganization (in_progress)",
+    "system_context_exposure (future)"
+  ],
+  "notes": "Deferred from discussion_hub_panel_reorganization planning. Improves aggregation with sub-agent summarization and hash-based caching."
+}

conductor/tracks/aggregation_smarter_summaries_20260322/plan.md

@@ -0,0 +1,49 @@
+# Implementation Plan: Smarter Aggregation with Sub-Agent Summarization
+
+## Phase 1: Hash-Based Summary Cache
+Focus: Implement file hashing and cache storage
+
+- [ ] Task: Research existing file hash implementations in codebase
+- [ ] Task: Design cache storage format (file-based vs project state)
+- [ ] Task: Implement hash computation for aggregation files
+- [ ] Task: Implement summary cache storage and retrieval
+- [ ] Task: Add cache invalidation when file content changes
+- [ ] Task: Write tests for hash computation and cache
+- [ ] Task: Conductor - User Manual Verification 'Phase 1: Hash-Based Summary Cache'
+
+## Phase 2: Sub-Agent Summarization
+Focus: Implement sub-agent summarization during aggregation
+
+- [ ] Task: Audit current aggregate.py flow
+- [ ] Task: Define summarization prompt strategy for code vs text files
+- [ ] Task: Implement sub-agent invocation during aggregation
+- [ ] Task: Handle provider-specific differences in sub-agent calls
+- [ ] Task: Write tests for sub-agent summarization
+- [ ] Task: Conductor - User Manual Verification 'Phase 2: Sub-Agent Summarization'
+
+## Phase 3: Tiered Aggregation Strategy
+Focus: Respect tier-level aggregation configuration
+
+- [ ] Task: Audit how tiers receive context currently
+- [ ] Task: Implement tier-level aggregation strategy selection
+- [ ] Task: Connect tier strategy to Persona configuration
+- [ ] Task: Write tests for tiered aggregation
+- [ ] Task: Conductor - User Manual Verification 'Phase 3: Tiered Aggregation Strategy'
+
+## Phase 4: UI Integration
+Focus: Expose cache status and controls in UI
+
+- [ ] Task: Add cache status indicator to Files & Media panel
+- [ ] Task: Add "Clear Summary Cache" button
+- [ ] Task: Add aggregation configuration to Project Settings or AI Settings
+- [ ] Task: Write tests for UI integration
+- [ ] Task: Conductor - User Manual Verification 'Phase 4: UI Integration'
+
+## Phase 5: Cache Persistence & Optimization
+Focus: Ensure cache persists and is performant
+
+- [ ] Task: Implement persistent cache storage to disk
+- [ ] Task: Add cache size management (max entries, LRU)
+- [ ] Task: Performance testing with large codebases
+- [ ] Task: Write tests for persistence
+- [ ] Task: Conductor - User Manual Verification 'Phase 5: Cache Persistence & Optimization'

conductor/tracks/aggregation_smarter_summaries_20260322/spec.md

@@ -0,0 +1,103 @@
+# Specification: Smarter Aggregation with Sub-Agent Summarization
+
+## 1. Overview
+
+This track improves the context aggregation system to use sub-agent passes for intelligent summarization and hash-based caching to avoid redundant work.
+
+**Current Problem:**
+- Aggregation is a simple pass that either injects full file content or a basic skeleton
+- No intelligence applied to determine what level of detail is needed
+- Same files get re-summarized on every discussion start even if unchanged
+
+**Goal:**
+- Use a sub-agent during aggregation pass for high-tier agents to generate succinct summaries
+- Cache summaries based on file hash - only re-summarize if file changed
+- Smart outline generation for code files, summary for text files
+
+## 2. Current State Audit
+
+### Existing Aggregation Behavior
+- `aggregate.py` handles context aggregation
+- `file_cache.py` provides AST parsing and skeleton generation
+- Per-file flags: `Auto-Aggregate` (summarize), `Force Full` (inject raw)
+- No caching of summarization results
+
+### Provider API Considerations
+- Different providers have different prompt/caching mechanisms
+- Need to verify how each provider handles system context and caching
+- May need provider-specific aggregation strategies
+
+## 3. Functional Requirements
+
+### 3.1 Hash-Based Summary Cache
+- Generate SHA256 hash of file content
+- Store summaries in a cache (file-based or in project state)
+- Before summarizing, check if file hash matches cached summary
+- Cache invalidation when file content changes
+
+### 3.2 Sub-Agent Summarization Pass
+- During aggregation, optionally invoke sub-agent for summarization
+- Sub-agent generates concise summary of file purpose and key points
+- Different strategies for:
+  - Code files: AST-based outline + key function signatures
+  - Text files: Paragraph-level summary
+  - Config files: Key-value extraction
+
+### 3.3 Tiered Aggregation Strategy
+- Tier 3/4 workers: Get skeleton outlines (fast, cheap)
+- Tier 2 (Tech Lead): Get summaries with key details
+- Tier 1 (Orchestrator): May get full content or enhanced summaries
+- Configurable per-agent via Persona
+
+### 3.4 Cache Persistence
+- Summaries persist across sessions
+- Stored in project directory or centralized cache location
+- Manual cache clear option in UI
+
+## 4. Data Model
+
+### 4.1 Summary Cache Entry
+```python
+{
+    "file_path": str,
+    "file_hash": str,  # SHA256 of content
+    "summary": str,
+    "outline": str,  # For code files
+    "generated_at": str,  # ISO timestamp
+    "generator_tier": str,  # Which tier generated it
+}
+```
+
+### 4.2 Aggregation Config
+```toml
+[aggregation]
+default_mode = "summarize"  # "full", "summarize", "outline"
+cache_enabled = true
+cache_dir = ".slop_cache"
+```
+
+## 5. UI Changes
+
+- Add "Clear Summary Cache" button in Files & Media or Context Composition
+- Show cached status indicator on files (similar to AST cache indicator)
+- Configuration in AI Settings or Project Settings
+
+## 6. Acceptance Criteria
+
+- [ ] File hash computed before summarization
+- [ ] Summary cache persists across app restarts
+- [ ] Sub-agent generates better summaries than basic skeleton
+- [ ] Aggregation respects tier-level configuration
+- [ ] Cache can be manually cleared
+- [ ] Provider APIs handle aggregated context correctly
+
+## 7. Out of Scope
+- Changes to provider API internals
+- Vector store / embeddings for RAG (separate track)
+- Changes to Session Hub / Discussion Hub layout
+
+## 8. Dependencies
+- `aggregate.py` - main aggregation logic
+- `file_cache.py` - AST parsing and caching
+- `ai_client.py` - sub-agent invocation
+- `models.py` - may need new config structures

conductor/tracks/discussion_hub_panel_reorganization_20260322/metadata.json

@@ -0,0 +1,22 @@
+{
+  "name": "discussion_hub_panel_reorganization",
+  "created": "2026-03-22",
+  "status": "in_progress",
+  "priority": "high",
+  "affected_files": [
+    "src/gui_2.py",
+    "src/models.py",
+    "src/project_manager.py",
+    "tests/test_gui_context_presets.py",
+    "tests/test_discussion_takes.py"
+  ],
+  "replaces": [
+    "session_context_snapshots_20260311",
+    "discussion_takes_branching_20260311"
+  ],
+  "related_tracks": [
+    "aggregation_smarter_summaries (future)",
+    "system_context_exposure (future)"
+  ],
+  "notes": "These earlier tracks were marked complete but the UI panel reorganization was not properly implemented. This track consolidates and properly executes the intended UX."
+}

conductor/tracks/discussion_hub_panel_reorganization_20260322/plan.md

@@ -0,0 +1,55 @@
+# Implementation Plan: Discussion Hub Panel Reorganization
+
+## Phase 1: Cleanup & Project Settings Rename
+Focus: Remove redundant ui_summary_only, rename Context Hub, establish project-level vs discussion-level separation
+
+- [ ] Task: Audit current ui_summary_only usages and document behavior to deprecate
+- [ ] Task: Remove ui_summary_only checkbox from _render_projects_panel (gui_2.py)
+- [ ] Task: Rename Context Hub to "Project Settings" in _gui_func tab bar
+- [ ] Task: Remove Context Presets tab from Project Settings (Context Hub)
+- [ ] Task: Update references in show_windows dict and any help text
+- [ ] Task: Write tests verifying ui_summary_only removal doesn't break existing functionality
+- [ ] Task: Conductor - User Manual Verification 'Phase 1: Cleanup & Project Settings Rename'
+
+## Phase 2: Merge Session Hub into Discussion Hub
+Focus: Move Session Hub tabs into Discussion Hub, eliminate separate Session Hub window
+
+- [ ] Task: Audit Session Hub (_render_session_hub) tab content
+- [ ] Task: Add Snapshot tab to Discussion Hub containing Aggregate MD + System Prompt preview
+- [ ] Task: Remove Session Hub window from _gui_func
+- [ ] Task: Add Discussion Hub tab bar structure (Discussion | Context Composition | Snapshot | Takes)
+- [ ] Task: Write tests for new tab structure rendering
+- [ ] Task: Conductor - User Manual Verification 'Phase 2: Merge Session Hub into Discussion Hub'
+
+## Phase 3: Context Composition Tab
+Focus: Per-discussion file filter with save/load preset functionality
+
+- [ ] Task: Write tests for Context Composition state management
+- [ ] Task: Create _render_context_composition_panel method
+- [ ] Task: Implement file/screenshot selection display (filtered from Files & Media)
+- [ ] Task: Implement per-file flags display (Auto-Aggregate, Force Full)
+- [ ] Task: Implement Save as Preset / Load Preset buttons
+- [ ] Task: Connect Context Presets storage to this panel
+- [ ] Task: Update Persona editor to reference Context Composition presets
+- [ ] Task: Write tests for Context Composition preset save/load
+- [ ] Task: Conductor - User Manual Verification 'Phase 3: Context Composition Tab'
+
+## Phase 4: Takes Timeline Integration
+Focus: DAW-style branching with proper visual timeline and synthesis
+
+- [ ] Task: Audit existing takes data structure and synthesis_formatter
+- [ ] Task: Enhance takes data model with parent_entry and parent_take tracking
+- [ ] Task: Implement Branch from Entry action in discussion history
+- [ ] Task: Implement visual timeline showing take divergence
+- [ ] Task: Integrate synthesis panel into Takes tab
+- [ ] Task: Implement take selection for synthesis
+- [ ] Task: Write tests for take branching and synthesis
+- [ ] Task: Conductor - User Manual Verification 'Phase 4: Takes Timeline Integration'
+
+## Phase 5: Final Integration & Cleanup
+Focus: Ensure all panels work together, remove dead code
+
+- [ ] Task: Run full test suite to verify no regressions
+- [ ] Task: Remove dead code from ui_summary_only references
+- [ ] Task: Update conductor/tracks.md to mark old session_context_snapshots and discussion_takes_branching as archived/replaced
+- [ ] Task: Conductor - User Manual Verification 'Phase 5: Final Integration & Cleanup'

conductor/tracks/discussion_hub_panel_reorganization_20260322/spec.md

@@ -0,0 +1,137 @@
+# Specification: Discussion Hub Panel Reorganization
+
+## 1. Overview
+
+This track addresses the fragmented implementation of Session Context Snapshots and Discussion Takes & Timeline Branching tracks (2026-03-11). Those tracks were marked complete but the UI panel layout was not properly reorganized.
+
+**Goal:** Create a coherent Discussion Hub that absorbs Session Hub functionality, establishes Files & Media as project-level file inventory, and properly implements Context Composition and DAW-style Takes branching.
+
+## 2. Current State Audit (as of 2026-03-22)
+
+### Already Implemented (DO NOT re-implement)
+- `ui_summary_only` checkbox in Projects panel
+- Session Hub as separate window with tabs: Aggregate MD | System Prompt
+- Context Hub with tabs: Projects | Paths | Context Presets
+- Context Presets save/load mechanism in project TOML
+- `_render_synthesis_panel()` method (gui_2.py:2612-2643) - basic synthesis UI
+- Takes data structure in `project['discussion']['discussions']`
+- Per-file `Auto-Aggregate` and `Force Full` flags in Files & Media
+
+### Gaps to Fill (This Track's Scope)
+1. `ui_summary_only` is redundant with per-file flags - deprecate it
+2. Context Hub renamed to "Project Settings" (remove Context Presets tab)
+3. Session Hub merged into Discussion Hub as tabs
+4. Files & Media stays separate as project-level inventory
+5. Context Composition tab in Discussion Hub for per-discussion filter
+6. Context Presets accessible via Context Composition (save/load filters)
+7. DAW-style Takes timeline properly integrated into Discussion Hub
+8. Synthesis properly integrated with Take selection
+
+## 3. Panel Layout Target
+
+| Panel | Location | Purpose |
+|-------|----------|---------|
+| **AI Settings** | Separate dockable | Provider, model, system prompts, tool presets, bias profiles |
+| **Files & Media** | Separate dockable | Project-level file inventory (addressable files) |
+| **Project Settings** | Context Hub → rename | Git dir, paths, project list (NO context stuff) |
+| **Discussion Hub** | Main hub | All discussion-related UI (tabs below) |
+| **MMA Dashboard** | Separate dockable | Multi-agent orchestration |
+| **Operations Hub** | Separate dockable | Tool calls, comms history, external tools |
+| **Diagnostics** | Separate dockable | Telemetry, logs |
+
+**Discussion Hub Tabs:**
+1. **Discussion** - Main conversation view (current implementation)
+2. **Context Composition** - File/screenshot filter + presets (NEW)
+3. **Snapshot** - Aggregate MD + System Prompt preview (moved from Session Hub)
+4. **Takes** - DAW-style timeline branching + synthesis (integrated, not separate panel)
+
+## 4. Functional Requirements
+
+### 4.1 Deprecate ui_summary_only
+- Remove `ui_summary_only` checkbox from Projects panel
+- Per-file flags (`Auto-Aggregate`, `Force Full`) are the intended mechanism
+- Document migration path for users
+
+### 4.2 Rename Context Hub → Project Settings
+- Context Hub tab bar: Projects | Paths
+- Remove "Context Presets" tab
+- All context-related functionality moves to Discussion Hub → Context Composition
+
+### 4.3 Merge Session Hub into Discussion Hub
+- Session Hub window eliminated
+- Its content becomes tabs in Discussion Hub:
+  - **Snapshot tab**: Aggregate MD preview, System Prompt preview, "Copy" buttons
+  - These were previously in Session Hub
+
+### 4.4 Context Composition Tab (NEW)
+- Shows currently selected files/screenshots for THIS discussion
+- Per-file flags: Auto-Aggregate, Force Full
+- **"Save as Preset"** / **"Load Preset"** buttons
+- Dropdown to select from saved presets
+- Relationship to Files & Media:
+  - Files & Media = the inventory (project-level)
+  - Context Composition = selected filter for current discussion
+
+### 4.5 Takes Timeline (DAW-Style)
+- **New Take**: Start fresh discussion thread
+- **Branch Take**: Fork from any discussion entry
+- **Switch Take**: Make a take the active discussion
+- **Rename/Delete Take**
+- All takes share the same Files & Media (not duplicated)
+- Non-destructive branching
+- Visual timeline showing divergence points
+
+### 4.6 Synthesis Integration
+- User selects 2+ takes via checkboxes
+- Click "Synthesize" button
+- AI generates "resolved" response considering all selected approaches
+- Result appears as new take
+- Accessible from Discussion Hub → Takes tab
+
+## 5. Data Model Changes
+
+### 5.1 Discussion State Structure
+```python
+# Per discussion in project['discussion']['discussions']
+{
+    "name": str,
+    "history": [
+        {"role": "user"|"assistant", "content": str, "ts": str, "files_injected": [...]}
+    ],
+    "parent_entry": Optional[int],  # index of parent message if branched
+    "parent_take": Optional[str],   # name of parent take if branched
+}
+```
+
+### 5.2 Context Preset Format
+```toml
+[context_preset.my_filter]
+files = ["path/to/file_a.py"]
+auto_aggregate = true
+force_full = false
+screenshots = ["path/to/shot1.png"]
+```
+
+## 6. Non-Functional Requirements
+- All changes must not break existing tests
+- New tests required for new functionality
+- Follow 1-space indentation Python code style
+- No comments unless explicitly requested
+
+## 7. Acceptance Criteria
+
+- [ ] `ui_summary_only` removed from Projects panel
+- [ ] Context Hub renamed to Project Settings
+- [ ] Session Hub window eliminated
+- [ ] Discussion Hub has 4 tabs: Discussion, Context Composition, Snapshot, Takes
+- [ ] Context Composition allows save/load of filter presets
+- [ ] Takes can be branched from any entry
+- [ ] Takes timeline shows divergence visually
+- [ ] Synthesis works with 2+ selected takes
+- [ ] All existing tests still pass
+- [ ] New tests cover new functionality
+
+## 8. Out of Scope
+- Aggregation improvements (sub-agent summarization, hash-based caching) - separate future track
+- System prompt exposure (`_SYSTEM_PROMPT` in ai_client.py) - separate future track
+- Session sophistication (Session as container for multiple discussions) - deferred

conductor/tracks/discussion_takes_branching_20260311/plan.md

@@ -1,25 +1,28 @@
 # Implementation Plan: Discussion Takes & Timeline Branching
 
-## Phase 1: Backend Support for Timeline Branching
-- [ ] Task: Write failing tests for extending the session state model to support branching (tree-like history or parallel linear "takes" with a shared ancestor).
-- [ ] Task: Implement backend logic to branch a session history at a specific message index into a new take ID.
-- [ ] Task: Implement backend logic to promote a specific take ID into an independent, top-level session.
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: Backend Support for Timeline Branching' (Protocol in workflow.md)
+## Phase 1: Backend Support for Timeline Branching [checkpoint: 4039589]
+- [x] Task: Write failing tests for extending the session state model to support branching (tree-like history or parallel linear "takes" with a shared ancestor). [fefa06b]
+- [x] Task: Implement backend logic to branch a session history at a specific message index into a new take ID. [fefa06b]
+- [x] Task: Implement backend logic to promote a specific take ID into an independent, top-level session. [fefa06b]
+- [x] Task: Conductor - User Manual Verification 'Phase 1: Backend Support for Timeline Branching' (Protocol in workflow.md)
 
-## Phase 2: GUI Implementation for Tabbed Takes
-- [ ] Task: Write GUI tests verifying the rendering and navigation of multiple tabs for a single session.
-- [ ] Task: Implement a tabbed interface within the Discussion window to switch between different takes of the active session.
-- [ ] Task: Add a "Split/Branch from here" action to individual message entries in the discussion history.
-- [ ] Task: Add a UI button/action to promote the currently active take to a new separate session.
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: GUI Implementation for Tabbed Takes' (Protocol in workflow.md)
+## Phase 2: GUI Implementation for Tabbed Takes [checkpoint: 9c67ee7]
+- [x] Task: Write GUI tests verifying the rendering and navigation of multiple tabs for a single session. [3225125]
+- [x] Task: Implement a tabbed interface within the Discussion window to switch between different takes of the active session. [3225125]
+- [x] Task: Add a "Split/Branch from here" action to individual message entries in the discussion history. [e48835f]
+- [x] Task: Add a UI button/action to promote the currently active take to a new separate session. [1f7880a]
+- [x] Task: Conductor - User Manual Verification 'Phase 2: GUI Implementation for Tabbed Takes' (Protocol in workflow.md)
 
-## Phase 3: Synthesis Workflow Formatting
-- [ ] Task: Write tests for a new text formatting utility that takes multiple history sequences and generates a compressed, diff-like text representation.
-- [ ] Task: Implement the sequence differencing and compression logic to clearly highlight variances between takes.
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: Synthesis Workflow Formatting' (Protocol in workflow.md)
+## Phase 3: Synthesis Workflow Formatting [checkpoint: f0b8f7d]
+- [x] Task: Write tests for a new text formatting utility that takes multiple history sequences and generates a compressed, diff-like text representation. [510527c]
+- [x] Task: Implement the sequence differencing and compression logic to clearly highlight variances between takes. [510527c]
+- [x] Task: Conductor - User Manual Verification 'Phase 3: Synthesis Workflow Formatting' (Protocol in workflow.md)
 
-## Phase 4: Synthesis UI & Agent Integration
-- [ ] Task: Write GUI tests for the multi-take selection interface and synthesis action.
-- [ ] Task: Implement a UI mechanism allowing users to select multiple takes and provide a synthesis prompt.
-- [ ] Task: Implement the execution pipeline to feed the compressed differences and user prompt to an AI agent, and route the generated synthesis to a new "take" tab.
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Synthesis UI & Agent Integration' (Protocol in workflow.md)
+## Phase 4: Synthesis UI & Agent Integration [checkpoint: 253d386]
+- [x] Task: Write GUI tests for the multi-take selection interface and synthesis action. [a452c72]
+- [x] Task: Implement a UI mechanism allowing users to select multiple takes and provide a synthesis prompt. [a452c72]
+- [x] Task: Implement the execution pipeline to feed the compressed differences and user prompt to an AI agent, and route the generated synthesis to a new "take" tab. [a452c72]
+- [x] Task: Conductor - User Manual Verification 'Phase 4: Synthesis UI & Agent Integration' (Protocol in workflow.md)
+
+## Phase: Review Fixes
+- [x] Task: Apply review suggestions [2a8af5f]

conductor/tracks/session_context_snapshots_20260311/plan.md

@@ -1,24 +1,24 @@
 # Implementation Plan: Session Context Snapshots & Visibility
 
 ## Phase 1: Backend Support for Context Presets
-- [ ] Task: Write failing tests for saving, loading, and listing Context Presets in the project configuration.
-- [ ] Task: Implement Context Preset storage logic (e.g., updating TOML schemas in `project_manager.py`) to manage file/screenshot lists.
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: Backend Support for Context Presets' (Protocol in workflow.md)
+- [x] Task: Write failing tests for saving, loading, and listing Context Presets in the project configuration. 93a590c
+- [x] Task: Implement Context Preset storage logic (e.g., updating TOML schemas in `project_manager.py`) to manage file/screenshot lists. 93a590c
+- [x] Task: Conductor - User Manual Verification 'Phase 1: Backend Support for Context Presets' (Protocol in workflow.md) 93a590c
 
 ## Phase 2: GUI Integration & Persona Assignment
-- [ ] Task: Write tests for the Context Hub UI components handling preset saving and loading.
-- [ ] Task: Implement the UI controls in the Context Hub to save current selections as a preset and load existing presets.
-- [ ] Task: Update the Persona configuration UI (`personas.py` / `gui_2.py`) to allow assigning a named Context Preset to an agent persona.
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: GUI Integration & Persona Assignment' (Protocol in workflow.md)
+- [x] Task: Write tests for the Context Hub UI components handling preset saving and loading. 573f5ee
+- [x] Task: Implement the UI controls in the Context Hub to save current selections as a preset and load existing presets. 573f5ee
+- [x] Task: Update the Persona configuration UI (`personas.py` / `gui_2.py`) to allow assigning a named Context Preset to an agent persona. 791e1b7
+- [x] Task: Conductor - User Manual Verification 'Phase 2: GUI Integration & Persona Assignment' (Protocol in workflow.md) 791e1b7
 
 ## Phase 3: Transparent Context Visibility
-- [ ] Task: Write tests to ensure the initial aggregate markdown, resolved system prompt, and file injection timestamps are accurately recorded in the session state.
-- [ ] Task: Implement UI elements in the Session Hub to expose the aggregated markdown and the active system prompt.
-- [ ] Task: Enhance the discussion timeline rendering in `gui_2.py` to visually indicate exactly when files and screenshots were injected into the context.
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: Transparent Context Visibility' (Protocol in workflow.md)
+- [x] Task: Write tests to ensure the initial aggregate markdown, resolved system prompt, and file injection timestamps are accurately recorded in the session state. 84b6266
+- [x] Task: Implement UI elements in the Session Hub to expose the aggregated markdown and the active system prompt. 84b6266
+- [x] Task: Enhance the discussion timeline rendering in `gui_2.py` to visually indicate exactly when files and screenshots were injected into the context. 84b6266
+- [x] Task: Conductor - User Manual Verification 'Phase 3: Transparent Context Visibility' (Protocol in workflow.md) 84b6266
 
 ## Phase 4: Agent-Focused Session Filtering
-- [ ] Task: Write tests for the GUI state filtering logic when focusing on a specific agent's session.
-- [ ] Task: Relocate the 'Focus Agent' feature from the Operations Hub to the MMA Dashboard.
-- [ ] Task: Implement the action to filter the Session and Discussion hubs based on the selected agent's context.
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Agent-Focused Session Filtering' (Protocol in workflow.md)
+- [x] Task: Write tests for the GUI state filtering logic when focusing on a specific agent's session. 038c909
+- [x] Task: Relocate the 'Focus Agent' feature from the Operations Hub to the MMA Dashboard. 038c909
+- [x] Task: Implement the action to filter the Session and Discussion hubs based on the selected agent's context. 038c909
+- [x] Task: Conductor - User Manual Verification 'Phase 4: Agent-Focused Session Filtering' (Protocol in workflow.md) 038c909

conductor/tracks/system_context_exposure_20260322/metadata.json

@@ -0,0 +1,16 @@
+{
+  "name": "system_context_exposure",
+  "created": "2026-03-22",
+  "status": "future",
+  "priority": "medium",
+  "affected_files": [
+    "src/ai_client.py",
+    "src/gui_2.py",
+    "src/models.py"
+  ],
+  "related_tracks": [
+    "discussion_hub_panel_reorganization (in_progress)",
+    "aggregation_smarter_summaries (future)"
+  ],
+  "notes": "Deferred from discussion_hub_panel_reorganization planning. The _SYSTEM_PROMPT in ai_client.py is hidden from users - this exposes it for customization."
+}

conductor/tracks/system_context_exposure_20260322/plan.md

@@ -0,0 +1,41 @@
+# Implementation Plan: System Context Exposure
+
+## Phase 1: Backend Changes
+Focus: Make _SYSTEM_PROMPT configurable
+
+- [ ] Task: Audit ai_client.py system prompt flow
+- [ ] Task: Move _SYSTEM_PROMPT to configurable storage
+- [ ] Task: Implement load/save of base system prompt
+- [ ] Task: Modify _get_combined_system_prompt() to use config
+- [ ] Task: Write tests for configurable system prompt
+- [ ] Task: Conductor - User Manual Verification 'Phase 1: Backend Changes'
+
+## Phase 2: UI Implementation
+Focus: Add base prompt editor to AI Settings
+
+- [ ] Task: Add UI controls to _render_system_prompts_panel
+- [ ] Task: Implement checkbox for "Use Default Base"
+- [ ] Task: Implement collapsible base prompt editor
+- [ ] Task: Add "Reset to Default" button
+- [ ] Task: Write tests for UI controls
+- [ ] Task: Conductor - User Manual Verification 'Phase 2: UI Implementation'
+
+## Phase 3: Persistence & Provider Testing
+Focus: Ensure persistence and cross-provider compatibility
+
+- [ ] Task: Verify base prompt persists across app restarts
+- [ ] Task: Test with Gemini provider
+- [ ] Task: Test with Anthropic provider
+- [ ] Task: Test with DeepSeek provider
+- [ ] Task: Test with Gemini CLI adapter
+- [ ] Task: Conductor - User Manual Verification 'Phase 3: Persistence & Provider Testing'
+
+## Phase 4: Safety & Defaults
+Focus: Ensure users can recover from bad edits
+
+- [ ] Task: Implement confirmation dialog before saving custom base
+- [ ] Task: Add validation for empty/invalid prompts
+- [ ] Task: Document the base prompt purpose in UI
+- [ ] Task: Add "Show Diff" between default and custom
+- [ ] Task: Write tests for safety features
+- [ ] Task: Conductor - User Manual Verification 'Phase 4: Safety & Defaults'

conductor/tracks/system_context_exposure_20260322/spec.md

@@ -0,0 +1,120 @@
+# Specification: System Context Exposure
+
+## 1. Overview
+
+This track exposes the hidden system prompt from `ai_client.py` to users for customization.
+
+**Current Problem:**
+- `_SYSTEM_PROMPT` in `ai_client.py` (lines ~118-143) is hardcoded
+- It contains foundational instructions: "You are a helpful coding assistant with access to a PowerShell tool..."
+- Users can only see/appending their custom portion via `_custom_system_prompt`
+- The base prompt that defines core agent capabilities is invisible
+
+**Goal:**
+- Make `_SYSTEM_PROMPT` visible and editable in the UI
+- Allow users to customize the foundational agent instructions
+- Maintain sensible defaults while enabling expert customization
+
+## 2. Current State Audit
+
+### Hidden System Prompt Location
+`src/ai_client.py`:
+```python
+_SYSTEM_PROMPT: str = (
+ "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. "
+ ...
+)
+```
+
+### Related State
+- `_custom_system_prompt` - user-defined append/injection
+- `_get_combined_system_prompt()` - merges both
+- `set_custom_system_prompt()` - setter for user portion
+
+### UI Current State
+- AI Settings → System Prompts shows global and project prompts
+- These are injected as `[USER SYSTEM PROMPT]` after `_SYSTEM_PROMPT`
+- But `_SYSTEM_PROMPT` itself is never shown
+
+## 3. Functional Requirements
+
+### 3.1 Base System Prompt Visibility
+- Add "Base System Prompt" section in AI Settings
+- Display current `_SYSTEM_PROMPT` content
+- Allow editing with syntax highlighting (it's markdown text)
+
+### 3.2 Default vs Custom Base
+- Maintain default base prompt as reference
+- User can reset to default if they mess it up
+- Show diff between default and custom
+
+### 3.3 Persistence
+- Custom base prompt stored in config or project TOML
+- Loaded on app start
+- Applied before `_custom_system_prompt` in `_get_combined_system_prompt()`
+
+### 3.4 Provider Considerations
+- Some providers handle system prompts differently
+- Verify behavior across Gemini, Anthropic, DeepSeek
+- May need provider-specific base prompts
+
+## 4. Data Model
+
+### 4.1 Config Storage
+```toml
+[ai_settings]
+base_system_prompt = """..."""
+use_default_base = true
+```
+
+### 4.2 Combined Prompt Order
+1. `_SYSTEM_PROMPT` (or custom base if enabled)
+2. `[USER SYSTEM PROMPT]` (from AI Settings global/project)
+3. Tooling strategy (from bias engine)
+
+## 5. UI Design
+
+**Location:** AI Settings panel → System Prompts section
+
+```
+┌─ System Prompts ──────────────────────────────┐
+│ ☑ Use Default Base System Prompt              │
+│                                              │
+│ Base System Prompt (collapsed by default):    │
+│ ┌──────────────────────────────────────────┐ │
+│ │ You are a helpful coding assistant...     │ │
+│ └──────────────────────────────────────────┘ │
+│                                              │
+│ [Show Editor] [Reset to Default]              │
+│                                              │
+│ Global System Prompt:                         │
+│ ┌──────────────────────────────────────────┐ │
+│ │ [current global prompt content]           │ │
+│ └──────────────────────────────────────────┘ │
+└──────────────────────────────────────────────┘
+```
+
+When "Show Editor" clicked:
+- Expand to full editor for base prompt
+- Syntax highlighting for markdown
+- Character count
+
+## 6. Acceptance Criteria
+
+- [ ] `_SYSTEM_PROMPT` visible in AI Settings
+- [ ] User can edit base system prompt
+- [ ] Changes persist across app restarts
+- [ ] "Reset to Default" restores original
+- [ ] Provider APIs receive modified prompt correctly
+- [ ] No regression in agent behavior with defaults
+
+## 7. Out of Scope
+- Changes to actual agent behavior logic
+- Changes to tool definitions or availability
+- Changes to aggregation or context handling
+
+## 8. Dependencies
+- `ai_client.py` - `_SYSTEM_PROMPT` and `_get_combined_system_prompt()`
+- `gui_2.py` - AI Settings panel rendering
+- `models.py` - Config structures

conductor/tracks/text_viewer_rich_rendering_20260313/plan.md

@@ -1,29 +1,29 @@
 # Implementation Plan: Advanced Text Viewer with Syntax Highlighting
 
 ## Phase 1: State & Interface Update
-- [ ] Task: Audit `src/gui_2.py` to ensure all `text_viewer_*` state variables are explicitly initialized in `App.__init__`.
-- [ ] Task: Implement: Update `App.__init__` to initialize `self.show_text_viewer`, `self.text_viewer_title`, `self.text_viewer_content`, and new `self.text_viewer_type` (defaulting to "text").
-- [ ] Task: Implement: Update `self.text_viewer_wrap` (defaulting to True) to allow independent word wrap.
-- [ ] Task: Implement: Update `_render_text_viewer(self, label: str, content: str, text_type: str = "text")` signature and caller usage.
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: State & Interface Update' (Protocol in workflow.md)
+- [x] Task: Audit `src/gui_2.py` to ensure all `text_viewer_*` state variables are explicitly initialized in `App.__init__`. e28af48
+- [x] Task: Implement: Update `App.__init__` to initialize `self.show_text_viewer`, `self.text_viewer_title`, `self.text_viewer_content`, and new `self.text_viewer_type` (defaulting to "text"). e28af48
+- [x] Task: Implement: Update `self.text_viewer_wrap` (defaulting to True) to allow independent word wrap. e28af48
+- [x] Task: Implement: Update `_render_text_viewer(self, label: str, content: str, text_type: str = "text")` signature and caller usage. e28af48
+- [x] Task: Conductor - User Manual Verification 'Phase 1: State & Interface Update' (Protocol in workflow.md) e28af48
 
 ## Phase 2: Core Rendering Logic (Code & MD)
-- [ ] Task: Write Tests: Create a simulation test in `tests/test_gui_text_viewer.py` to verify the viewer opens and switches rendering paths based on `text_type`.
-- [ ] Task: Implement: In `src/gui_2.py`, refactor the text viewer window loop to:
-  - Use `MarkdownRenderer.render` if `text_type == "markdown"`.
-  - Use a cached `ImGuiColorTextEdit.TextEditor` if `text_type` matches a code language.
-  - Fallback to `imgui.input_text_multiline` for plain text.
-- [ ] Task: Implement: Ensure the `TextEditor` instance is properly cached using a unique key for the text viewer to maintain state.
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: Core Rendering Logic' (Protocol in workflow.md)
+- [x] Task: Write Tests: Create a simulation test in `tests/test_gui_text_viewer.py` to verify the viewer opens and switches rendering paths based on `text_type`. a91b8dc
+- [x] Task: Implement: In `src/gui_2.py`, refactor the text viewer window loop to: a91b8dc
+  - Use `MarkdownRenderer.render` if `text_type == "markdown"`. a91b8dc
+  - Use a cached `ImGuiColorTextEdit.TextEditor` if `text_type` matches a code language. a91b8dc
+  - Fallback to `imgui.input_text_multiline` for plain text. a91b8dc
+- [x] Task: Implement: Ensure the `TextEditor` instance is properly cached using a unique key for the text viewer to maintain state. a91b8dc
+- [x] Task: Conductor - User Manual Verification 'Phase 2: Core Rendering Logic' (Protocol in workflow.md) a91b8dc
 
 ## Phase 3: UI Features (Copy, Line Numbers, Wrap)
-- [ ] Task: Write Tests: Update `tests/test_gui_text_viewer.py` to verify the copy-to-clipboard functionality and word wrap toggle.
-- [ ] Task: Implement: Add a "Copy" button to the text viewer title bar or a small toolbar at the top of the window.
-- [ ] Task: Implement: Add a "Word Wrap" checkbox inside the text viewer window.
-- [ ] Task: Implement: Configure the `TextEditor` instance to show line numbers and be read-only.
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: UI Features' (Protocol in workflow.md)
+- [x] Task: Write Tests: Update `tests/test_gui_text_viewer.py` to verify the copy-to-clipboard functionality and word wrap toggle. a91b8dc
+- [x] Task: Implement: Add a "Copy" button to the text viewer title bar or a small toolbar at the top of the window. a91b8dc
+- [x] Task: Implement: Add a "Word Wrap" checkbox inside the text viewer window. a91b8dc
+- [x] Task: Implement: Configure the `TextEditor` instance to show line numbers and be read-only. a91b8dc
+- [x] Task: Conductor - User Manual Verification 'Phase 3: UI Features' (Protocol in workflow.md) a91b8dc
 
 ## Phase 4: Integration & Rollout
-- [ ] Task: Implement: Update all existing calls to `_render_text_viewer` in `src/gui_2.py` (e.g., in `_render_files_panel`, `_render_tool_calls_panel`) to pass the correct `text_type` based on file extension or content.
-- [ ] Task: Implement: Add "Markdown Preview" support for system prompt presets using the new text viewer logic.
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Integration & Rollout' (Protocol in workflow.md)
+- [x] Task: Implement: Update all existing calls to `_render_text_viewer` in `src/gui_2.py` (e.g., in `_render_files_panel`, `_render_tool_calls_panel`) to pass the correct `text_type` based on file extension or content. 2826ad5
+- [x] Task: Implement: Add "Markdown Preview" support for system prompt presets using the new text viewer logic. 2826ad5
+- [x] Task: Conductor - User Manual Verification 'Phase 4: Integration & Rollout' (Protocol in workflow.md) 2826ad5

conductor/tracks/thinking_trace_handling_20260313/plan.md

@@ -1,26 +1,23 @@
 # Implementation Plan: Rich Thinking Trace Handling
 
-## Phase 1: Core Parsing & Model Update
-- [ ] Task: Audit `src/models.py` and `src/project_manager.py` to identify current message serialization schemas.
-- [ ] Task: Write Tests: Verify that raw AI responses with `<thinking>`, `<thought>`, and `Thinking:` markers are correctly parsed into segmented data structures (Thinking vs. Response).
-- [ ] Task: Implement: Add `ThinkingSegment` model and update `ChatMessage` schema in `src/models.py` to support optional thinking traces.
-- [ ] Task: Implement: Update parsing logic in `src/ai_client.py` or a dedicated utility to extract segments from raw provider responses.
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: Core Parsing & Model Update' (Protocol in workflow.md)
+## Status: COMPLETE (2026-03-14)
 
-## Phase 2: Persistence & History Integration
-- [ ] Task: Write Tests: Verify that `ProjectManager` correctly serializes and deserializes messages with thinking segments to/from TOML history files.
-- [ ] Task: Implement: Update `src/project_manager.py` to handle the new `ChatMessage` schema during session save/load.
-- [ ] Task: Implement: Ensure `src/aggregate.py` or relevant context builders include thinking traces in the "Discussion History" sent back to the AI.
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: Persistence & History Integration' (Protocol in workflow.md)
+## Summary
+Implemented thinking trace parsing, model, persistence, and GUI rendering for AI responses containing `<thinking>`, `<thought>`, and `Thinking:` markers.
 
-## Phase 3: GUI Rendering - Comms & Discussion
-- [ ] Task: Write Tests: Verify the GUI rendering logic correctly handles messages with and without thinking segments.
-- [ ] Task: Implement: Create a reusable `_render_thinking_trace` helper in `src/gui_2.py` using a collapsible header (e.g., `imgui.collapsing_header`).
-- [ ] Task: Implement: Integrate the thinking trace renderer into the **Comms History** panel in `src/gui_2.py`.
-- [ ] Task: Implement: Integrate the thinking trace renderer into the **Discussion Hub** message loop in `src/gui_2.py`.
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: GUI Rendering - Comms & Discussion' (Protocol in workflow.md)
+## Files Created/Modified:
+- `src/thinking_parser.py` - Parser for thinking traces
+- `src/models.py` - ThinkingSegment model
+- `src/gui_2.py` - _render_thinking_trace helper + integration
+- `tests/test_thinking_trace.py` - 7 parsing tests
+- `tests/test_thinking_persistence.py` - 4 persistence tests  
+- `tests/test_thinking_gui.py` - 4 GUI tests
 
-## Phase 4: Final Polish & Theming
-- [ ] Task: Implement: Apply specialized styling (e.g., tinted background or italicized text) to expanded thinking traces to distinguish them from direct responses.
-- [ ] Task: Implement: Ensure thinking trace headers show a "Calculating..." or "Monologue" indicator while an agent is active.
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Final Polish & Theming' (Protocol in workflow.md)
+## Implementation Details:
+- **Parser**: Extracts thinking segments from `<thinking>`, `<thought>`, `Thinking:` markers
+- **Model**: `ThinkingSegment` dataclass with content and marker fields
+- **GUI**: `_render_thinking_trace` with collapsible "Monologue" header
+- **Styling**: Tinted background (dark brown), gold/amber text
+- **Indicator**: Existing "THINKING..." in Discussion Hub
+
+## Total Tests: 15 passing

config.toml

@@ -5,8 +5,8 @@ temperature = 0.0
 top_p = 1.0
 max_tokens = 32000
 history_trunc_limit = 900000
-active_preset = "Default"
-system_prompt = ""
+active_preset = ""
+system_prompt = "Overridden Prompt"
 
 [projects]
 paths = [
@@ -23,7 +23,7 @@ active = "C:/projects/gencpp/gencpp_sloppy.toml"
 separate_message_panel = false
 separate_response_panel = false
 separate_tool_calls_panel = false
-bg_shader_enabled = true
+bg_shader_enabled = false
 crt_filter_enabled = false
 separate_task_dag = false
 separate_usage_analytics = false
@@ -37,9 +37,9 @@ separate_external_tools = false
 "Context Hub" = true
 "Files & Media" = true
 "AI Settings" = true
-"MMA Dashboard" = true
-"Task DAG" = false
-"Usage Analytics" = false
+"MMA Dashboard" = false
+"Task DAG" = true
+"Usage Analytics" = true
 "Tier 1" = false
 "Tier 2" = false
 "Tier 3" = false
@@ -51,21 +51,22 @@ separate_external_tools = false
 "Discussion Hub" = true
 "Operations Hub" = true
 Message = false
-Response = true
+Response = false
 "Tool Calls" = false
 Theme = true
-"Log Management" = true
+"Log Management" = false
 Diagnostics = false
 "External Tools" = false
 "Shader Editor" = false
+"Session Hub" = false
 
 [theme]
 palette = "Nord Dark"
-font_path = "C:/projects/manual_slop/assets/fonts/MapleMono-Regular.ttf"
-font_size = 18.0
+font_path = "fonts/Inter-Regular.ttf"
+font_size = 16.0
 scale = 1.0
-transparency = 0.5400000214576721
-child_transparency = 0.5899999737739563
+transparency = 1.0
+child_transparency = 1.0
 
 [mma]
 max_workers = 4

manualslop_layout.ini

@@ -44,18 +44,18 @@ Collapsed=0
 DockId=0x00000001,0
 
 [Window][Message]
-Pos=661,1426
+Pos=711,694
 Size=716,455
 Collapsed=0
 
 [Window][Response]
-Pos=2437,925
-Size=1111,773
+Pos=245,1014
+Size=1492,948
 Collapsed=0
 
 [Window][Tool Calls]
-Pos=520,1144
-Size=663,232
+Pos=1028,1668
+Size=1397,340
 Collapsed=0
 DockId=0x00000006,0
 
@@ -74,8 +74,8 @@ Collapsed=0
 DockId=0xAFC85805,2
 
 [Window][Theme]
-Pos=0,703
-Size=630,737
+Pos=0,976
+Size=635,951
 Collapsed=0
 DockId=0x00000002,2
 
@@ -85,14 +85,14 @@ Size=900,700
 Collapsed=0
 
 [Window][Diagnostics]
-Pos=1649,24
-Size=580,1284
+Pos=2177,26
+Size=1162,1777
 Collapsed=0
-DockId=0x00000010,2
+DockId=0x00000010,0
 
 [Window][Context Hub]
-Pos=0,703
-Size=630,737
+Pos=0,976
+Size=635,951
 Collapsed=0
 DockId=0x00000002,1
 
@@ -103,26 +103,26 @@ Collapsed=0
 DockId=0x0000000D,0
 
 [Window][Discussion Hub]
-Pos=1263,22
-Size=709,1418
+Pos=1936,24
+Size=1468,1903
 Collapsed=0
 DockId=0x00000013,0
 
 [Window][Operations Hub]
-Pos=632,22
-Size=629,1418
+Pos=637,24
+Size=1297,1903
 Collapsed=0
 DockId=0x00000005,0
 
 [Window][Files & Media]
-Pos=0,703
-Size=630,737
+Pos=0,976
+Size=635,951
 Collapsed=0
 DockId=0x00000002,0
 
 [Window][AI Settings]
-Pos=0,22
-Size=630,679
+Pos=0,24
+Size=635,950
 Collapsed=0
 DockId=0x00000001,0
 
@@ -132,16 +132,16 @@ Size=416,325
 Collapsed=0
 
 [Window][MMA Dashboard]
-Pos=1974,22
-Size=586,1418
+Pos=3360,26
+Size=480,2134
 Collapsed=0
 DockId=0x00000010,0
 
 [Window][Log Management]
-Pos=1974,22
-Size=586,1418
+Pos=3360,26
+Size=480,2134
 Collapsed=0
-DockId=0x00000010,1
+DockId=0x00000010,0
 
 [Window][Track Proposal]
 Pos=709,326
@@ -175,8 +175,8 @@ Size=381,329
 Collapsed=0
 
 [Window][Last Script Output]
-Pos=2810,265
-Size=800,562
+Pos=1076,794
+Size=1085,1154
 Collapsed=0
 
 [Window][Text Viewer - Log Entry #1 (request)]
@@ -190,7 +190,7 @@ Size=1005,366
 Collapsed=0
 
 [Window][Text Viewer - Entry #11]
-Pos=60,60
+Pos=1010,564
 Size=1529,925
 Collapsed=0
 
@@ -220,13 +220,13 @@ Size=900,700
 Collapsed=0
 
 [Window][Text Viewer - text]
-Pos=60,60
+Pos=1297,550
 Size=900,700
 Collapsed=0
 
 [Window][Text Viewer - system]
-Pos=377,705
-Size=900,340
+Pos=901,1502
+Size=876,536
 Collapsed=0
 
 [Window][Text Viewer - Entry #15]
@@ -240,8 +240,8 @@ Size=900,700
 Collapsed=0
 
 [Window][Text Viewer - tool_calls]
-Pos=60,60
-Size=900,700
+Pos=1106,942
+Size=831,482
 Collapsed=0
 
 [Window][Text Viewer - Tool Script #1]
@@ -285,7 +285,7 @@ Size=900,700
 Collapsed=0
 
 [Window][Text Viewer - Tool Call #1 Details]
-Pos=165,1081
+Pos=963,716
 Size=727,725
 Collapsed=0
 
@@ -330,8 +330,8 @@ Size=967,499
 Collapsed=0
 
 [Window][Usage Analytics]
-Pos=1739,1107
-Size=586,269
+Pos=2678,26
+Size=1162,2134
 Collapsed=0
 DockId=0x0000000F,0
 
@@ -366,7 +366,7 @@ Size=900,700
 Collapsed=0
 
 [Window][Text Viewer - Entry #4]
-Pos=1127,922
+Pos=1165,782
 Size=900,700
 Collapsed=0
 
@@ -376,13 +376,28 @@ Size=1593,1240
 Collapsed=0
 
 [Window][Text Viewer - Entry #5]
-Pos=60,60
-Size=900,700
+Pos=989,778
+Size=1366,1032
 Collapsed=0
 
 [Window][Shader Editor]
 Pos=457,710
-Size=493,252
+Size=573,280
+Collapsed=0
+
+[Window][Text Viewer - list_directory]
+Pos=1376,796
+Size=882,656
+Collapsed=0
+
+[Window][Text Viewer - Last Output]
+Pos=60,60
+Size=900,700
+Collapsed=0
+
+[Window][Text Viewer - Entry #2]
+Pos=1518,488
+Size=900,700
 Collapsed=0
 
 [Table][0xFB6E3870,4]
@@ -416,11 +431,11 @@ Column 3  Width=20
 Column 4  Weight=1.0000
 
 [Table][0x2A6000B6,4]
-RefScale=16
-Column 0  Width=48
-Column 1  Width=68
+RefScale=18
+Column 0  Width=54
+Column 1  Width=76
 Column 2  Weight=1.0000
-Column 3  Width=120
+Column 3  Width=274
 
 [Table][0x8BCC69C7,6]
 RefScale=13
@@ -432,18 +447,18 @@ Column 4  Weight=1.0000
 Column 5  Width=50
 
 [Table][0x3751446B,4]
-RefScale=16
-Column 0  Width=48
-Column 1  Width=72
+RefScale=18
+Column 0  Width=54
+Column 1  Width=81
 Column 2  Weight=1.0000
-Column 3  Width=120
+Column 3  Width=135
 
 [Table][0x2C515046,4]
-RefScale=16
-Column 0  Width=48
+RefScale=18
+Column 0  Width=54
 Column 1  Weight=1.0000
-Column 2  Width=118
-Column 3  Width=48
+Column 2  Width=132
+Column 3  Width=54
 
 [Table][0xD99F45C5,4]
 Column 0  Sort=0v
@@ -464,9 +479,9 @@ Column 1  Width=100
 Column 2  Weight=1.0000
 
 [Table][0xA02D8C87,3]
-RefScale=16
-Column 0  Width=180
-Column 1  Width=120
+RefScale=18
+Column 0  Width=202
+Column 1  Width=135
 Column 2  Weight=1.0000
 
 [Table][0xD0277E63,2]
@@ -480,13 +495,13 @@ Column 0  Width=150
 Column 1  Weight=1.0000
 
 [Table][0x8D8494AB,2]
-RefScale=16
-Column 0  Width=132
+RefScale=18
+Column 0  Width=148
 Column 1  Weight=1.0000
 
 [Table][0x2C261E6E,2]
-RefScale=16
-Column 0  Width=99
+RefScale=18
+Column 0  Width=111
 Column 1  Weight=1.0000
 
 [Table][0x9CB1E6FD,2]
@@ -498,20 +513,20 @@ Column 1  Weight=1.0000
 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=0,22 Size=2560,1418 Split=X
-  DockNode          ID=0x00000003 Parent=0xAFC85805 SizeRef=1640,1183 Split=X
+DockSpace           ID=0xAFC85805 Window=0x079D3A04 Pos=0,24 Size=3404,1903 Split=X
+  DockNode          ID=0x00000003 Parent=0xAFC85805 SizeRef=2175,1183 Split=X
     DockNode        ID=0x0000000B Parent=0x00000003 SizeRef=404,1186 Split=X Selected=0xF4139CA2
-      DockNode      ID=0x00000007 Parent=0x0000000B SizeRef=630,858 Split=Y Selected=0x8CA2375C
-        DockNode    ID=0x00000001 Parent=0x00000007 SizeRef=824,525 CentralNode=1 Selected=0x7BD57D6A
-        DockNode    ID=0x00000002 Parent=0x00000007 SizeRef=824,737 Selected=0x8CA2375C
-      DockNode      ID=0x0000000E Parent=0x0000000B SizeRef=1340,858 Split=X Selected=0x418C7449
-        DockNode    ID=0x00000012 Parent=0x0000000E SizeRef=629,402 Split=Y Selected=0x418C7449
+      DockNode      ID=0x00000007 Parent=0x0000000B SizeRef=1071,858 Split=Y Selected=0x8CA2375C
+        DockNode    ID=0x00000001 Parent=0x00000007 SizeRef=824,950 CentralNode=1 Selected=0x7BD57D6A
+        DockNode    ID=0x00000002 Parent=0x00000007 SizeRef=824,951 Selected=0x8CA2375C
+      DockNode      ID=0x0000000E Parent=0x0000000B SizeRef=2767,858 Split=X Selected=0x418C7449
+        DockNode    ID=0x00000012 Parent=0x0000000E SizeRef=1297,402 Split=Y Selected=0x418C7449
           DockNode  ID=0x00000005 Parent=0x00000012 SizeRef=876,1749 Selected=0x418C7449
           DockNode  ID=0x00000006 Parent=0x00000012 SizeRef=876,362 Selected=0x1D56B311
-        DockNode    ID=0x00000013 Parent=0x0000000E SizeRef=709,402 Selected=0x6F2B5B04
+        DockNode    ID=0x00000013 Parent=0x0000000E SizeRef=1468,402 Selected=0x6F2B5B04
     DockNode        ID=0x0000000D Parent=0x00000003 SizeRef=435,1186 Selected=0x363E93D6
-  DockNode          ID=0x00000004 Parent=0xAFC85805 SizeRef=586,1183 Split=Y Selected=0x3AEC3498
-    DockNode        ID=0x00000010 Parent=0x00000004 SizeRef=1199,1689 Selected=0x2C0206CE
+  DockNode          ID=0x00000004 Parent=0xAFC85805 SizeRef=1162,1183 Split=Y Selected=0x3AEC3498
+    DockNode        ID=0x00000010 Parent=0x00000004 SizeRef=1199,1689 Selected=0xB4CBF21A
     DockNode        ID=0x00000011 Parent=0x00000004 SizeRef=1199,420 Split=X Selected=0xDEB547B6
       DockNode      ID=0x0000000C Parent=0x00000011 SizeRef=916,380 Selected=0x655BC6E9
       DockNode      ID=0x0000000F Parent=0x00000011 SizeRef=281,380 Selected=0xDEB547B6

opencode.json

@@ -71,5 +71,6 @@
       "logs/**",
       "*.log"
     ]
-  }
+  },
+  "plugin": ["superpowers@git+https://github.com/obra/superpowers.git"]
 }

project.toml

@@ -17,6 +17,8 @@ paths = []
 base_dir = "."
 paths = []
 
+[context_presets]
+
 [gemini_cli]
 binary_path = "gemini"
 

project_history.toml

@@ -9,5 +9,5 @@ active = "main"
 
 [discussions.main]
 git_commit = ""
-last_updated = "2026-03-12T20:34:43"
+last_updated = "2026-03-21T15:21:34"
 history = []

src/api_hooks.py

@@ -225,6 +225,9 @@ class HookHandler(BaseHTTPRequestHandler):
       for key, attr in gettable.items():
        val = _get_app_attr(app, attr, None)
        result[key] = _serialize_for_api(val)
+      result['show_text_viewer'] = _get_app_attr(app, 'show_text_viewer', False)
+      result['text_viewer_title'] = _get_app_attr(app, 'text_viewer_title', '')
+      result['text_viewer_type'] = _get_app_attr(app, 'text_viewer_type', 'markdown')
      finally: event.set()
     lock = _get_app_attr(app, "_pending_gui_tasks_lock")
     tasks = _get_app_attr(app, "_pending_gui_tasks")
@@ -250,7 +253,7 @@ class HookHandler(BaseHTTPRequestHandler):
     self.end_headers()
     files = _get_app_attr(app, "files", [])
     screenshots = _get_app_attr(app, "screenshots", [])
-    self.wfile.write(json.dumps({"files": files, "screenshots": screenshots}).encode("utf-8"))
+    self.wfile.write(json.dumps({"files": _serialize_for_api(files), "screenshots": _serialize_for_api(screenshots)}).encode("utf-8"))
    elif self.path == "/api/metrics/financial":
     self.send_response(200)
     self.send_header("Content-Type", "application/json")

src/app_controller.py

@@ -25,6 +25,7 @@ from src import project_manager
 from src import performance_monitor
 from src import models
 from src import presets
+from src import thinking_parser
 from src.file_cache import ASTParser
 from src import ai_client
 from src import shell_runner
@@ -242,6 +243,8 @@ class AppController:
   self.ai_status: str = 'idle'
   self.ai_response: str = ''
   self.last_md: str = ''
+  self.last_aggregate_markdown: str = ''
+  self.last_resolved_system_prompt: str = ''
   self.last_md_path: Optional[Path] = None
   self.last_file_items: List[Any] = []
   self.send_thread: Optional[threading.Thread] = None
@@ -251,6 +254,7 @@ class AppController:
   self.show_text_viewer: bool = False
   self.text_viewer_title: str = ''
   self.text_viewer_content: str = ''
+  self.text_viewer_type: str = 'text'
   self._pending_comms: List[Dict[str, Any]] = []
   self._pending_tool_calls: List[Dict[str, Any]] = []
   self._pending_history_adds: List[Dict[str, Any]] = []
@@ -374,7 +378,10 @@ class AppController:
    'ui_separate_tier1': 'ui_separate_tier1',
    'ui_separate_tier2': 'ui_separate_tier2',
    'ui_separate_tier3': 'ui_separate_tier3',
-   'ui_separate_tier4': 'ui_separate_tier4'
+   'ui_separate_tier4': 'ui_separate_tier4',
+   'show_text_viewer': 'show_text_viewer',
+   'text_viewer_title': 'text_viewer_title',
+   'text_viewer_type': 'text_viewer_type'
   }
   self._gettable_fields = dict(self._settable_fields)
   self._gettable_fields.update({
@@ -421,7 +428,10 @@ class AppController:
    'ui_separate_tier1': 'ui_separate_tier1',
    'ui_separate_tier2': 'ui_separate_tier2',
    'ui_separate_tier3': 'ui_separate_tier3',
-   'ui_separate_tier4': 'ui_separate_tier4'
+   'ui_separate_tier4': 'ui_separate_tier4',
+   'show_text_viewer': 'show_text_viewer',
+   'text_viewer_title': 'text_viewer_title',
+   'text_viewer_type': 'text_viewer_type'
   })
   self.perf_monitor = performance_monitor.get_monitor()
   self._perf_profiling_enabled = False
@@ -610,16 +620,6 @@ class AppController:
       self._token_stats_dirty = True
       if not is_streaming:
        self._autofocus_response_tab = True
-      # ONLY add to history when turn is complete
-     if self.ui_auto_add_history and not stream_id and not is_streaming:
-      role = payload.get("role", "AI")
-      with self._pending_history_adds_lock:
-       self._pending_history_adds.append({
-         "role": role, 
-         "content": self.ai_response, 
-         "collapsed": True, 
-         "ts": project_manager.now_ts()
-        })
     elif action in ("mma_stream", "mma_stream_append"):
     # Some events might have these at top level, some in a 'payload' dict
      stream_id = task.get("stream_id") or task.get("payload", {}).get("stream_id")
@@ -1467,9 +1467,22 @@ class AppController:
   
   if kind == "response" and "usage" in payload:
    u = payload["usage"]
-   for k in ["input_tokens", "output_tokens", "cache_read_input_tokens", "cache_creation_input_tokens", "total_tokens"]:
-    if k in u:
-     self.session_usage[k] += u.get(k, 0) or 0
+   inp = u.get("input_tokens", u.get("prompt_tokens", 0))
+   out = u.get("output_tokens", u.get("completion_tokens", 0))
+   cache_read = u.get("cache_read_input_tokens", 0)
+   cache_create = u.get("cache_creation_input_tokens", 0)
+   total = u.get("total_tokens", 0)
+
+   # Store normalized usage back in payload for history rendering
+   u["input_tokens"] = inp
+   u["output_tokens"] = out
+   u["cache_read_input_tokens"] = cache_read
+
+   self.session_usage["input_tokens"] += inp
+   self.session_usage["output_tokens"] += out
+   self.session_usage["cache_read_input_tokens"] += cache_read
+   self.session_usage["cache_creation_input_tokens"] += cache_create
+   self.session_usage["total_tokens"] += total
    input_t = u.get("input_tokens", 0)
    output_t = u.get("output_tokens", 0)
    model = payload.get("model", "unknown")
@@ -1490,7 +1503,27 @@ class AppController:
       "ts": entry.get("ts", project_manager.now_ts())
      })
 
+  if kind == "response":
+   if self.ui_auto_add_history:
+    role = payload.get("role", "AI")
+    text_content = payload.get("text", "")
+    if text_content.strip():
+     segments, parsed_response = thinking_parser.parse_thinking_trace(text_content)
+     entry_obj = {
+      "role": role,
+      "content": parsed_response.strip() if parsed_response else "",
+      "collapsed": True,
+      "ts": entry.get("ts", project_manager.now_ts())
+     }
+     if segments:
+      entry_obj["thinking_segments"] = [{"content": s.content, "marker": s.marker} for s in segments]
+     
+     if entry_obj["content"] or segments:
+      with self._pending_history_adds_lock:
+       self._pending_history_adds.append(entry_obj)
+
   if kind in ("tool_result", "tool_call"):
+   if self.ui_auto_add_history:
     role = "Tool" if kind == "tool_result" else "Vendor API"
     content = ""
     if kind == "tool_result":
@@ -2158,6 +2191,20 @@ class AppController:
   discussions[name] = project_manager.default_discussion()
   self._switch_discussion(name)
 
+ def _branch_discussion(self, index: int) -> None:
+  self._flush_disc_entries_to_project()
+  # Generate a unique branch name
+  base_name = self.active_discussion.split("_take_")[0]
+  counter = 1
+  new_name = f"{base_name}_take_{counter}"
+  disc_sec = self.project.get("discussion", {})
+  discussions = disc_sec.get("discussions", {})
+  while new_name in discussions:
+   counter += 1
+   new_name = f"{base_name}_take_{counter}"
+
+  project_manager.branch_discussion(self.project, self.active_discussion, new_name, index)
+  self._switch_discussion(new_name)
  def _rename_discussion(self, old_name: str, new_name: str) -> None:
   disc_sec = self.project.get("discussion", {})
   discussions = disc_sec.get("discussions", {})
@@ -2485,6 +2532,11 @@ class AppController:
   # Build discussion history text separately
   history = flat.get("discussion", {}).get("history", [])
   discussion_text = aggregate.build_discussion_text(history)
+  
+  csp = filter(bool, [self.ui_global_system_prompt.strip(), self.ui_project_system_prompt.strip()])
+  self.last_resolved_system_prompt = "\n\n".join(csp)
+  self.last_aggregate_markdown = full_md
+  
   return full_md, path, file_items, stable_md, discussion_text
 
  def _cb_plan_epic(self) -> None:

src/events.py

@@ -91,7 +91,14 @@ class AsyncEventQueue:
   """
   self._queue.put((event_name, payload))
   if self.websocket_server:
-   self.websocket_server.broadcast("events", {"event": event_name, "payload": payload})
+   # Ensure payload is JSON serializable for websocket broadcast
+   serializable_payload = payload
+   if hasattr(payload, 'to_dict'):
+    serializable_payload = payload.to_dict()
+   elif hasattr(payload, '__dict__'):
+    serializable_payload = vars(payload)
+   
+   self.websocket_server.broadcast("events", {"event": event_name, "payload": serializable_payload})
 
  def get(self) -> Tuple[str, Any]:
   """

src/gui_2.py

@@ -26,8 +26,11 @@ from src import log_pruner
 from src import models
 from src import app_controller
 from src import mcp_client
+from src import aggregate
 from src import markdown_helper
 from src import bg_shader
+from src import thinking_parser
+from src import thinking_parser
 import re
 import subprocess
 if sys.platform == "win32":
@@ -38,7 +41,7 @@ else:
  win32con = None
 
 from pydantic import BaseModel
-from imgui_bundle import imgui, hello_imgui, immapp, imgui_node_editor as ed
+from imgui_bundle import imgui, hello_imgui, immapp, imgui_node_editor as ed, imgui_color_text_edit as ced
 
 PROVIDERS: list[str] = ["gemini", "anthropic", "gemini_cli", "deepseek", "minimax"]
 COMMS_CLAMP_CHARS: int = 300
@@ -105,11 +108,29 @@ class App:
   self.controller.init_state()
   self.show_windows.setdefault("Diagnostics", False)
   self.controller.start_services(self)
+  self.controller._predefined_callbacks['_render_text_viewer'] = self._render_text_viewer
+  self.controller._predefined_callbacks['save_context_preset'] = self.save_context_preset
+  self.controller._predefined_callbacks['load_context_preset'] = self.load_context_preset
+  self.controller._predefined_callbacks['set_ui_file_paths'] = lambda p: setattr(self, 'ui_file_paths', p)
+  self.controller._predefined_callbacks['set_ui_screenshot_paths'] = lambda p: setattr(self, 'ui_screenshot_paths', p)
+  def simulate_save_preset(name: str):
+   from src import models
+   self.files = [models.FileItem(path='test.py')]
+   self.screenshots = ['test.png']
+   self.save_context_preset(name)
+  self.controller._predefined_callbacks['simulate_save_preset'] = simulate_save_preset
   self.show_preset_manager_window = False
   self.show_tool_preset_manager_window = False
   self.show_persona_editor_window = False
+  self.show_text_viewer = False
+  self.text_viewer_title = ''
+  self.text_viewer_content = ''
+  self.text_viewer_type = 'text'
+  self.text_viewer_wrap = True
+  self._text_viewer_editor: Optional[ced.TextEditor] = None
   self.ui_active_tool_preset = ""
   self.ui_active_bias_profile = ""
+  self.ui_active_context_preset = ""
   self.ui_active_persona = ""
   self._editing_persona_name = ""
   self._editing_persona_description = ""
@@ -121,6 +142,7 @@ class App:
   self._editing_persona_max_tokens = 4096
   self._editing_persona_tool_preset_id = ""
   self._editing_persona_bias_profile_id = ""
+  self._editing_persona_context_preset_id = ""
   self._editing_persona_preferred_models_list: list[dict] = []
   self._editing_persona_scope = "project"
   self._editing_persona_is_new = True
@@ -193,6 +215,7 @@ class App:
   self.show_windows.setdefault("Tier 4: QA", False)
   self.show_windows.setdefault('External Tools', False)
   self.show_windows.setdefault('Shader Editor', False)
+  self.show_windows.setdefault('Session Hub', False)
   self.ui_multi_viewport = gui_cfg.get("multi_viewport", False)
   self.layout_presets = self.config.get("layout_presets", {})
   self._new_preset_name = ""
@@ -212,8 +235,9 @@ class App:
   self.ui_tool_filter_category = "All"
   self.ui_discussion_split_h = 300.0
   self.shader_uniforms = {'crt': 1.0, 'scanline': 0.5, 'bloom': 0.8}
-
- def _handle_approve_tool(self, user_data=None) -> None:
+  self.shader_uniforms = {'crt': 1.0, 'scanline': 0.5, 'bloom': 0.8}
+  self.ui_new_context_preset_name = ""
+  self._focus_md_cache: dict[str, str] = {}
   """UI-level wrapper for approving a pending tool execution ask."""
   self._handle_approve_ask()
 
@@ -271,6 +295,54 @@ class App:
    pass
   self.controller.shutdown()
 
+ def save_context_preset(self, name: str) -> None:
+  sys.stderr.write(f"[DEBUG] save_context_preset called with: {name}\n")
+  sys.stderr.flush()
+  if 'context_presets' not in self.controller.project:
+   self.controller.project['context_presets'] = {}
+  self.controller.project['context_presets'][name] = {
+   'files': [f.to_dict() if hasattr(f, 'to_dict') else {'path': str(f)} for f in self.files],
+   'screenshots': list(self.screenshots)
+  }
+  self.controller._save_active_project()
+  sys.stderr.write(f"[DEBUG] save_context_preset finished. Project keys: {list(self.controller.project.keys())}\n")
+  sys.stderr.flush()
+
+ def load_context_preset(self, name: str) -> None:
+  presets = self.controller.project.get('context_presets', {})
+  if name in presets:
+   preset = presets[name]
+   self.files = [models.FileItem.from_dict(f) if isinstance(f, dict) else models.FileItem(path=str(f)) for f in preset.get('files', [])]
+   self.screenshots = list(preset.get('screenshots', []))
+
+ def delete_context_preset(self, name: str) -> None:
+  if 'context_presets' in self.controller.project:
+   self.controller.project['context_presets'].pop(name, None)
+   self.controller._save_active_project()
+ @property
+ def ui_file_paths(self) -> list[str]:
+  return [f.path if hasattr(f, 'path') else str(f) for f in self.files]
+
+ @ui_file_paths.setter
+ def ui_file_paths(self, paths: list[str]) -> None:
+  old_files = {f.path: f for f in self.files if hasattr(f, 'path')}
+  new_files = []
+  now = time.time()
+  for p in paths:
+   if p in old_files:
+    new_files.append(old_files[p])
+   else:
+    new_files.append(models.FileItem(path=p, injected_at=now))
+  self.files = new_files
+
+ @property
+ def ui_screenshot_paths(self) -> list[str]:
+  return self.screenshots
+
+ @ui_screenshot_paths.setter
+ def ui_screenshot_paths(self, paths: list[str]) -> None:
+  self.screenshots = paths
+
  def _test_callback_func_write_to_file(self, data: str) -> None:
   """A dummy function that a custom_callback would execute for testing."""
   # Ensure the directory exists if running from a different cwd
@@ -279,8 +351,9 @@ class App:
    f.write(data)
    # ---------------------------------------------------------------- helpers
 
- def _render_text_viewer(self, label: str, content: str) -> None:
-  if imgui.button("[+]##" + str(id(content))):
+ def _render_text_viewer(self, label: str, content: str, text_type: str = 'text', force_open: bool = False) -> None:
+  self.text_viewer_type = text_type
+  if imgui.button("[+]##" + str(id(content))) or force_open:
    self.show_text_viewer = True
    self.text_viewer_title = label
    self.text_viewer_content = content
@@ -290,6 +363,7 @@ class App:
   imgui.same_line()
   if imgui.button("[+]##" + label + id_suffix):
    self.show_text_viewer = True
+   self.text_viewer_type = 'markdown' if label in ('message', 'text', 'content', 'system') else 'json' if label in ('tool_calls', 'data') else 'powershell' if label == 'script' else 'text'
    self.text_viewer_title = label
    self.text_viewer_content = content
   
@@ -304,21 +378,57 @@ class App:
   if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
 
   if len(content) > COMMS_CLAMP_CHARS:
-   imgui.begin_child(f"heavy_text_child_{label}_{id_suffix}", imgui.ImVec2(0, 80), True)
    if is_md:
+    imgui.begin_child(f"heavy_text_child_{label}_{id_suffix}", imgui.ImVec2(0, 180), True, imgui.WindowFlags_.always_vertical_scrollbar)
     markdown_helper.render(content, context_id=ctx_id)
-   else:
-    markdown_helper.render_code(content, context_id=ctx_id)
     imgui.end_child()
+   else:
+    imgui.input_text_multiline(f"##heavy_text_input_{label}_{id_suffix}", content, imgui.ImVec2(-1, 180), imgui.InputTextFlags_.read_only)
   else:
    if is_md:
     markdown_helper.render(content, context_id=ctx_id)
    else:
-    markdown_helper.render_code(content, context_id=ctx_id)
+    if self.ui_word_wrap:
+     imgui.push_text_wrap_pos(imgui.get_content_region_avail().x)
+     imgui.text(content)
+     imgui.pop_text_wrap_pos()
+    else:
+     imgui.text(content)
   
   if is_nerv: imgui.pop_style_color()
     # ---------------------------------------------------------------- gui
 
+ def _render_thinking_trace(self, segments: list[dict], entry_index: int, is_standalone: bool = False) -> None:
+  if not segments:
+   return
+  imgui.push_style_color(imgui.Col_.child_bg, vec4(40, 35, 25, 180))
+  imgui.push_style_color(imgui.Col_.text, vec4(200, 200, 150))
+  imgui.indent()
+  show_content = True
+  if not is_standalone:
+   header_label = f"Monologue ({len(segments)} traces)###thinking_header_{entry_index}"
+   show_content = imgui.collapsing_header(header_label)
+  
+  if show_content:
+   h = 150 if is_standalone else 100
+   imgui.begin_child(f"thinking_content_{entry_index}", imgui.ImVec2(0, h), True)
+   for idx, seg in enumerate(segments):
+    content = seg.get("content", "")
+    marker = seg.get("marker", "thinking")
+    imgui.push_id(f"think_{entry_index}_{idx}")
+    imgui.text_colored(vec4(180, 150, 80), f"[{marker}]")
+    if self.ui_word_wrap:
+     imgui.push_text_wrap_pos(imgui.get_content_region_avail().x)
+     imgui.text_colored(vec4(200, 200, 150), content)
+     imgui.pop_text_wrap_pos()
+    else:
+     imgui.text_colored(vec4(200, 200, 150), content)
+    imgui.pop_id()
+    imgui.separator()
+   imgui.end_child()
+  imgui.unindent()
+  imgui.pop_style_color(2)
+
 
  def _render_selectable_label(self, label: str, value: str, width: float = 0.0, multiline: bool = False, height: float = 0.0, color: Optional[imgui.ImVec4] = None) -> None:
   imgui.push_id(label + str(hash(value)))
@@ -540,6 +650,9 @@ class App:
       if imgui.begin_tab_item('Paths')[0]:
        self._render_paths_panel()
        imgui.end_tab_item()
+      if imgui.begin_tab_item('Context Presets')[0]:
+       self._render_context_presets_panel()
+       imgui.end_tab_item()
       imgui.end_tab_bar()
     imgui.end()
    if self.show_windows.get("Files & Media", False):
@@ -662,21 +775,6 @@ class App:
    if self.show_windows.get("Operations Hub", False):
     exp, opened = imgui.begin("Operations Hub", self.show_windows["Operations Hub"])
     self.show_windows["Operations Hub"] = bool(opened)
-    if exp:
-     imgui.text("Focus Agent:")
-     imgui.same_line()
-     focus_label = self.ui_focus_agent or "All"
-     if imgui.begin_combo("##focus_agent", focus_label, imgui.ComboFlags_.width_fit_preview):
-      if imgui.selectable("All", self.ui_focus_agent is None)[0]:
-       self.ui_focus_agent = None
-      for tier in ["Tier 2", "Tier 3", "Tier 4"]:
-       if imgui.selectable(tier, self.ui_focus_agent == tier)[0]:
-        self.ui_focus_agent = tier
-      imgui.end_combo()
-     imgui.same_line()
-     if self.ui_focus_agent:
-      if imgui.button("x##clear_focus"):
-       self.ui_focus_agent = None
     if exp:
      imgui.push_style_var(imgui.StyleVar_.item_spacing, imgui.ImVec2(10, 4))
      ch1, self.ui_separate_tool_calls_panel = imgui.checkbox("Pop Out Tool Calls", self.ui_separate_tool_calls_panel)
@@ -747,6 +845,8 @@ class App:
    if self.show_windows.get("Diagnostics", False):
     self._render_diagnostics_panel()
 
+   self._render_session_hub()
+
    self.perf_monitor.end_frame()
    # ---- Modals / Popups
    with self._pending_dialog_lock:
@@ -959,7 +1059,35 @@ class App:
     expanded, opened = imgui.begin(f"Text Viewer - {self.text_viewer_title}", self.show_text_viewer)
     self.show_text_viewer = bool(opened)
     if expanded:
-     if self.ui_word_wrap:
+     # Toolbar
+     if imgui.button("Copy"):
+      imgui.set_clipboard_text(self.text_viewer_content)
+     imgui.same_line()
+     _, self.text_viewer_wrap = imgui.checkbox("Word Wrap", self.text_viewer_wrap)
+     imgui.separator()
+
+     renderer = markdown_helper.get_renderer()
+     tv_type = getattr(self, "text_viewer_type", "text")
+     
+     if tv_type == 'markdown':
+      imgui.begin_child("tv_md_scroll", imgui.ImVec2(-1, -1), True)
+      markdown_helper.render(self.text_viewer_content, context_id='text_viewer')
+      imgui.end_child()
+     elif tv_type in renderer._lang_map:
+      if self._text_viewer_editor is None:
+       self._text_viewer_editor = ced.TextEditor()
+       self._text_viewer_editor.set_read_only_enabled(True)
+       self._text_viewer_editor.set_show_line_numbers_enabled(True)
+      
+      # Sync text and language
+      lang_id = renderer._lang_map[tv_type]
+      if self._text_viewer_editor.get_text().strip() != self.text_viewer_content.strip():
+       self._text_viewer_editor.set_text(self.text_viewer_content)
+      self._text_viewer_editor.set_language_definition(lang_id)
+      
+      self._text_viewer_editor.render('##tv_editor', a_size=imgui.ImVec2(-1, -1))
+     else:
+      if self.text_viewer_wrap:
        imgui.begin_child("tv_wrap", imgui.ImVec2(-1, -1), False)
        imgui.push_text_wrap_pos(imgui.get_content_region_avail().x)
        imgui.text(self.text_viewer_content)
@@ -1100,15 +1228,13 @@ class App:
     imgui.separator()
     imgui.text("Prompt Content:")
     imgui.same_line()
-    if imgui.button("MD Preview" if not self._prompt_md_preview else "Edit Mode"):
-     self._prompt_md_preview = not self._prompt_md_preview
+    if imgui.button("Pop out MD Preview"):
+     self.text_viewer_title = f"Preset: {self._editing_preset_name}"
+     self.text_viewer_content = self._editing_preset_system_prompt
+     self.text_viewer_type = "markdown"
+     self.show_text_viewer = True
     
     rem_y = imgui.get_content_region_avail().y
-    if self._prompt_md_preview:
-     if imgui.begin_child("prompt_preview", imgui.ImVec2(-1, rem_y), True):
-      markdown_helper.render(self._editing_preset_system_prompt, context_id="prompt_preset_preview")
-      imgui.end_child()
-    else:
     _, self._editing_preset_system_prompt = imgui.input_text_multiline("##pcont", self._editing_preset_system_prompt, imgui.ImVec2(-1, rem_y))
     imgui.end_child()
 
@@ -1347,6 +1473,7 @@ class App:
     if imgui.button("New Persona", imgui.ImVec2(-1, 0)):
      self._editing_persona_name = ""; self._editing_persona_system_prompt = ""
      self._editing_persona_tool_preset_id = ""; self._editing_persona_bias_profile_id = ""
+     self._editing_persona_context_preset_id = ""
      self._editing_persona_preferred_models_list = [{"provider": self.current_provider, "model": self.current_model, "temperature": 0.7, "top_p": 1.0, "max_output_tokens": 4096, "history_trunc_limit": 900000}]
      self._editing_persona_scope = "project"; self._editing_persona_is_new = True
     imgui.separator()
@@ -1355,6 +1482,7 @@ class App:
      if name and imgui.selectable(f"{name}##p_list", name == self._editing_persona_name and not getattr(self, '_editing_persona_is_new', False))[0]:
       p = personas[name]; self._editing_persona_name = p.name; self._editing_persona_system_prompt = p.system_prompt or ""
       self._editing_persona_tool_preset_id = p.tool_preset or ""; self._editing_persona_bias_profile_id = p.bias_profile or ""
+      self._editing_persona_context_preset_id = getattr(p, 'context_preset', '') or ""
       import copy; self._editing_persona_preferred_models_list = copy.deepcopy(p.preferred_models) if p.preferred_models else []
       self._editing_persona_scope = self.controller.persona_manager.get_persona_scope(p.name); self._editing_persona_is_new = False
     imgui.end_child()
@@ -1440,6 +1568,10 @@ class App:
      imgui.table_next_column(); imgui.text("Bias Profile:"); bn = ["None"] + sorted(self.controller.bias_profiles.keys())
      b_idx = bn.index(self._editing_persona_bias_profile_id) if getattr(self, '_editing_persona_bias_profile_id', '') in bn else 0
      imgui.set_next_item_width(-1); _, b_idx = imgui.combo("##pbp", b_idx, bn); self._editing_persona_bias_profile_id = bn[b_idx] if b_idx > 0 else ""
+     imgui.table_next_row()
+     imgui.table_next_column(); imgui.text("Context Preset:"); cn = ["None"] + sorted(self.controller.project.get("context_presets", {}).keys())
+     c_idx = cn.index(self._editing_persona_context_preset_id) if getattr(self, '_editing_persona_context_preset_id', '') in cn else 0
+     imgui.set_next_item_width(-1); _, c_idx = imgui.combo("##pcp", c_idx, cn); self._editing_persona_context_preset_id = cn[c_idx] if c_idx > 0 else ""
      imgui.end_table()
     
     if imgui.button("Manage Tools & Biases", imgui.ImVec2(-1, 0)): self.show_tool_preset_manager_window = True
@@ -1467,7 +1599,7 @@ class App:
    if imgui.button("Save##pers", imgui.ImVec2(100, 0)):
     if self._editing_persona_name.strip():
      try:
-      import copy; persona = models.Persona(name=self._editing_persona_name.strip(), system_prompt=self._editing_persona_system_prompt, tool_preset=self._editing_persona_tool_preset_id or None, bias_profile=self._editing_persona_bias_profile_id or None, preferred_models=copy.deepcopy(self._editing_persona_preferred_models_list))
+      import copy; persona = models.Persona(name=self._editing_persona_name.strip(), system_prompt=self._editing_persona_system_prompt, tool_preset=self._editing_persona_tool_preset_id or None, bias_profile=self._editing_persona_bias_profile_id or None, context_preset=self._editing_persona_context_preset_id or None, preferred_models=copy.deepcopy(self._editing_persona_preferred_models_list))
       self.controller._cb_save_persona(persona, getattr(self, '_editing_persona_scope', 'project')); self.ai_status = f"Saved: {persona.name}"
      except Exception as e: self.ai_status = f"Error: {e}"
     else: self.ai_status = "Name required"
@@ -1625,6 +1757,30 @@ class App:
    self.ai_status = "paths reset to defaults"
 
   if self.perf_profiling_enabled: self.perf_monitor.end_component("_render_paths_panel")
+
+ def _render_context_presets_panel(self) -> None:
+  imgui.text_colored(C_IN, "Context Presets")
+  imgui.separator()
+  changed, new_name = imgui.input_text("Preset Name##new_ctx", self.ui_new_context_preset_name)
+  if changed: self.ui_new_context_preset_name = new_name
+  imgui.same_line()
+  if imgui.button("Save Current"):
+   if self.ui_new_context_preset_name.strip():
+    self.save_context_preset(self.ui_new_context_preset_name.strip())
+  
+  imgui.separator()
+  presets = self.controller.project.get('context_presets', {})
+  for name in sorted(presets.keys()):
+   preset = presets[name]
+   n_files = len(preset.get('files', []))
+   n_shots = len(preset.get('screenshots', []))
+   imgui.text(f"{name} ({n_files} files, {n_shots} shots)")
+   imgui.same_line()
+   if imgui.button(f"Load##{name}"):
+    self.load_context_preset(name)
+   imgui.same_line()
+   if imgui.button(f"Delete##{name}"):
+    self.delete_context_preset(name)
  def _render_track_proposal_modal(self) -> None:
   if self._show_track_proposal_modal:
    imgui.open_popup("Track Proposal")
@@ -1929,6 +2085,50 @@ class App:
   if self.perf_profiling_enabled: self.perf_monitor.end_component("_render_diagnostics_panel")
   imgui.end()
 
+ def _render_session_hub(self) -> None:
+  if self.show_windows.get('Session Hub', False):
+   exp, opened = imgui.begin('Session Hub', self.show_windows['Session Hub'])
+   self.show_windows['Session Hub'] = bool(opened)
+   if exp:
+    if imgui.begin_tab_bar('session_hub_tabs'):
+     if imgui.begin_tab_item('Aggregate MD')[0]:
+      display_md = self.last_aggregate_markdown
+      if self.ui_focus_agent:
+       tier_usage = self.mma_tier_usage.get(self.ui_focus_agent)
+       if tier_usage:
+        persona_name = tier_usage.get("persona")
+        if persona_name:
+         persona = self.controller.personas.get(persona_name)
+         if persona and persona.context_preset:
+          cp_name = persona.context_preset
+          if cp_name in self._focus_md_cache:
+           display_md = self._focus_md_cache[cp_name]
+          else:
+           # Generate focused aggregate
+           flat = src.project_manager.flat_config(self.controller.project, self.active_discussion)
+           cp = self.controller.project.get('context_presets', {}).get(cp_name)
+           if cp:
+            flat["files"]["paths"] = cp.get("files", [])
+            flat["screenshots"]["paths"] = cp.get("screenshots", [])
+            full_md, _, _ = src.aggregate.run(flat)
+            self._focus_md_cache[cp_name] = full_md
+            display_md = full_md
+      if imgui.button("Copy"):
+       imgui.set_clipboard_text(display_md)
+      imgui.begin_child("last_agg_md", imgui.ImVec2(0, 0), True)
+      markdown_helper.render(display_md, context_id="session_hub_agg")
+      imgui.end_child()
+      imgui.end_tab_item()
+     if imgui.begin_tab_item('System Prompt')[0]:
+      if imgui.button("Copy"):
+       imgui.set_clipboard_text(self.last_resolved_system_prompt)
+      imgui.begin_child("last_sys_prompt", imgui.ImVec2(0, 0), True)
+      markdown_helper.render(self.last_resolved_system_prompt, context_id="session_hub_sys")
+      imgui.end_child()
+      imgui.end_tab_item()
+     imgui.end_tab_bar()
+   imgui.end()
+
  def _render_markdown_test(self) -> None:
   imgui.text("Markdown Test Panel")
   imgui.separator()
@@ -2062,12 +2262,10 @@ def hello():
    if theme.is_nerv_active():
     c = vec4(255, 50, 50, alpha) # More vibrant for NERV
    imgui.text_colored(c, "THINKING...")
-   imgui.separator()
-   # Prior session viewing mode
+   imgui.same_line()
+
   if self.is_viewing_prior_session:
    imgui.push_style_color(imgui.Col_.child_bg, vec4(50, 40, 20))
-   imgui.text_colored(vec4(255, 200, 100), "VIEWING PRIOR SESSION")
-   imgui.same_line()
    if imgui.button("Exit Prior Session"):
     self.controller.cb_exit_prior_session()
     self._comms_log_dirty = True
@@ -2106,17 +2304,65 @@ def hello():
      imgui.pop_id()
    imgui.end_child()
    imgui.pop_style_color()
+   if self.perf_profiling_enabled: self.perf_monitor.end_component("_render_discussion_panel")
    return
+
   if not self.is_viewing_prior_session and imgui.collapsing_header("Discussions", imgui.TreeNodeFlags_.default_open):
    names = self._get_discussion_names()
-   if imgui.begin_combo("##disc_sel", self.active_discussion):
+   grouped_discussions = {}
    for name in names:
-     is_selected = (name == self.active_discussion)
-     if imgui.selectable(name, is_selected)[0]:
-      self._switch_discussion(name)
+    base = name.split("_take_")[0]
+    grouped_discussions.setdefault(base, []).append(name)
+    
+   active_base = self.active_discussion.split("_take_")[0]
+   if active_base not in grouped_discussions:
+    active_base = names[0] if names else ""
+
+   base_names = sorted(grouped_discussions.keys())
+   if imgui.begin_combo("##disc_sel", active_base):
+    for bname in base_names:
+     is_selected = (bname == active_base)
+     if imgui.selectable(bname, is_selected)[0]:
+      target = bname if bname in names else grouped_discussions[bname][0]
+      if target != self.active_discussion:
+       self._switch_discussion(target)
      if is_selected:
       imgui.set_item_default_focus()
     imgui.end_combo()
+
+   # Sync variables in case combo selection changed self.active_discussion
+   active_base = self.active_discussion.split("_take_")[0]
+   current_takes = grouped_discussions.get(active_base, [])
+
+   if imgui.begin_tab_bar("discussion_takes_tabs"):
+    for take_name in current_takes:
+     label = "Original" if take_name == active_base else take_name.replace(f"{active_base}_", "").replace("_", " ").title()
+     flags = imgui.TabItemFlags_.set_selected if take_name == self.active_discussion else 0
+     res = imgui.begin_tab_item(f"{label}###{take_name}", None, flags)
+     if res[0]:
+      if take_name != self.active_discussion:
+       self._switch_discussion(take_name)
+      imgui.end_tab_item()
+    
+    res_s = imgui.begin_tab_item("Synthesis###Synthesis")
+    if res_s[0]:
+     self._render_synthesis_panel()
+     imgui.end_tab_item()
+
+    imgui.end_tab_bar()
+
+   if "_take_" in self.active_discussion:
+    if imgui.button("Promote Take"):
+     base_name = self.active_discussion.split("_take_")[0]
+     new_name = f"{base_name}_promoted"
+     counter = 1
+     while new_name in names:
+      new_name = f"{base_name}_promoted_{counter}"
+      counter += 1
+     project_manager.promote_take(self.project, self.active_discussion, new_name)
+     self._switch_discussion(new_name)
+    imgui.same_line()
+
    if self.active_track:
     imgui.same_line()
     changed, self._track_discussion_active = imgui.checkbox("Track Discussion", self._track_discussion_active)
@@ -2131,10 +2377,13 @@ def hello():
       self._flush_disc_entries_to_project()
       # Restore project discussion
       self._switch_discussion(self.active_discussion)
+      self.ai_status = "track discussion disabled"
+
    disc_sec = self.project.get("discussion", {})
    disc_data = disc_sec.get("discussions", {}).get(self.active_discussion, {})
    git_commit = disc_data.get("git_commit", "")
    last_updated = disc_data.get("last_updated", "")
+   
    imgui.text_colored(C_LBL, "commit:")
    imgui.same_line()
    self._render_selectable_label('git_commit_val', git_commit[:12] if git_commit else '(none)', width=100, color=(C_IN if git_commit else C_LBL))
@@ -2147,9 +2396,11 @@ def hello():
       disc_data["git_commit"] = cmt
       disc_data["last_updated"] = project_manager.now_ts()
       self.ai_status = f"commit: {cmt[:12]}"
+   
    imgui.text_colored(C_LBL, "updated:")
    imgui.same_line()
    imgui.text_colored(C_SUB, last_updated if last_updated else "(never)")
+   
    ch, self.ui_disc_new_name_input = imgui.input_text("##new_disc", self.ui_disc_new_name_input)
    imgui.same_line()
    if imgui.button("Create"):
@@ -2162,6 +2413,7 @@ def hello():
    imgui.same_line()
    if imgui.button("Delete"):
     self._delete_discussion(self.active_discussion)
+
   if not self.is_viewing_prior_session:
    imgui.separator()
    if imgui.button("+ Entry"):
@@ -2181,6 +2433,7 @@ def hello():
     self._flush_to_config()
     models.save_config(self.config)
     self.ai_status = "discussion saved"
+   
    ch, self.ui_auto_add_history = imgui.checkbox("Auto-add message & response to history", self.ui_auto_add_history)
    # Truncation controls
    imgui.text("Keep Pairs:")
@@ -2193,15 +2446,19 @@ def hello():
     with self._disc_entries_lock:
      self.disc_entries = truncate_entries(self.disc_entries, self.ui_disc_truncate_pairs)
     self.ai_status = f"history truncated to {self.ui_disc_truncate_pairs} pairs"
+   
    imgui.separator()
    if imgui.collapsing_header("Roles"):
     imgui.begin_child("roles_scroll", imgui.ImVec2(0, 100), True)
     for i, r in enumerate(self.disc_roles):
-     if imgui.button(f"x##r{i}"):
+     imgui.push_id(f"role_{i}")
+     if imgui.button("X"):
       self.disc_roles.pop(i)
+      imgui.pop_id()
       break
      imgui.same_line()
      imgui.text(r)
+     imgui.pop_id()
     imgui.end_child()
     ch, self.ui_disc_new_role_input = imgui.input_text("##new_role", self.ui_disc_new_role_input)
     imgui.same_line()
@@ -2210,14 +2467,27 @@ def hello():
      if r and r not in self.disc_roles:
       self.disc_roles.append(r)
       self.ui_disc_new_role_input = ""
+   
    imgui.separator()
    imgui.begin_child("disc_scroll", imgui.ImVec2(0, 0), False)
+
+   # Filter entries based on focused agent persona
+   display_entries = self.disc_entries
+   if self.ui_focus_agent:
+    tier_usage = self.mma_tier_usage.get(self.ui_focus_agent)
+    if tier_usage:
+     persona_name = tier_usage.get("persona")
+     if persona_name:
+      # Show User messages and the focused agent's responses
+      display_entries = [e for e in self.disc_entries if e.get("role") == persona_name or e.get("role") == "User"]
+
    clipper = imgui.ListClipper()
-   clipper.begin(len(self.disc_entries))
+   clipper.begin(len(display_entries))
    while clipper.step():
     for i in range(clipper.display_start, clipper.display_end):
-     entry = self.disc_entries[i]
-     imgui.push_id(str(i))
+     entry = display_entries[i]
+     # Use the index in the original list for ID if possible, but here i is index in display_entries
+     imgui.push_id(f"disc_{i}") 
      collapsed = entry.get("collapsed", False)
      read_mode = entry.get("read_mode", False)
      if imgui.button("+" if collapsed else "-"):
@@ -2231,14 +2501,33 @@ def hello():
        if imgui.selectable(r, r == entry["role"])[0]:
         entry["role"] = r
       imgui.end_combo()
+     
      if not collapsed:
       imgui.same_line()
       if imgui.button("[Edit]" if read_mode else "[Read]"):
        entry["read_mode"] = not read_mode
+     
      ts_str = entry.get("ts", "")
      if ts_str:
       imgui.same_line()
       imgui.text_colored(vec4(120, 120, 100), str(ts_str))
+      # Visual indicator for file injections
+      e_dt = project_manager.parse_ts(ts_str)
+      if e_dt:
+       e_unix = e_dt.timestamp()
+       next_unix = float('inf')
+       if i + 1 < len(self.disc_entries):
+        n_ts = self.disc_entries[i+1].get("ts", "")
+        n_dt = project_manager.parse_ts(n_ts)
+        if n_dt: next_unix = n_dt.timestamp()
+       injected_here = [f for f in self.files if hasattr(f, 'injected_at') and f.injected_at and e_unix <= f.injected_at < next_unix]
+       if injected_here:
+        imgui.same_line()
+        imgui.text_colored(vec4(100, 255, 100), f"[{len(injected_here)}+]")
+        if imgui.is_item_hovered():
+         tooltip = "Files injected at this point:\n" + "\n".join([f.path for f in injected_here])
+         imgui.set_tooltip(tooltip)
+
      if collapsed:
       imgui.same_line()
       if imgui.button("Ins"):
@@ -2249,12 +2538,24 @@ def hello():
        imgui.pop_id()
        break # Break from inner loop, clipper will re-step
       imgui.same_line()
-      preview = entry["content"].replace("\\n", " ")[:60]
+      if imgui.button("Branch"):
+       self._branch_discussion(i)
+      imgui.same_line()
+      preview = entry["content"].replace("\n", " ")[:60]
       if len(entry["content"]) > 60: preview += "..."
+      if not preview.strip() and entry.get("thinking_segments"):
+       preview = entry["thinking_segments"][0]["content"].replace("\n", " ")[:60]
+       if len(entry["thinking_segments"][0]["content"]) > 60: preview += "..."
       imgui.text_colored(vec4(160, 160, 150), preview)
      if not collapsed:
+      thinking_segments = entry.get("thinking_segments", [])
+      has_content = bool(entry.get("content", "").strip())
+      is_standalone = bool(thinking_segments) and not has_content
+      if thinking_segments:
+       self._render_thinking_trace(thinking_segments, i, is_standalone=is_standalone)
       if read_mode:
        content = entry["content"]
+       if content.strip():
         pattern = re.compile(r"\[Definition: (.*?) from (.*?) \(line (\d+)\)\](\s+```[\s\S]*?```)?")
         matches = list(pattern.finditer(content))
         is_nerv = theme.is_nerv_active()
@@ -2281,9 +2582,9 @@ def hello():
             if res:
              self.text_viewer_title = path
              self.text_viewer_content = res
+             self.text_viewer_type = Path(path).suffix.lstrip('.') if Path(path).suffix else 'text'
              self.show_text_viewer = True
            if code_block:
-           # Render code block with highlighting
             if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
             markdown_helper.render(code_block, context_id=f'disc_{i}_c_{m_idx}')
             if is_nerv: imgui.pop_style_color()
@@ -2296,13 +2597,50 @@ def hello():
          if self.ui_word_wrap: imgui.pop_text_wrap_pos()
          imgui.end_child()
       else:
+       if not is_standalone:
         ch, entry["content"] = imgui.input_text_multiline("##content", entry["content"], imgui.ImVec2(-1, 150))
      imgui.separator()
      imgui.pop_id()
+   
    if self._scroll_disc_to_bottom:
     imgui.set_scroll_here_y(1.0)
     self._scroll_disc_to_bottom = False
+   
    imgui.end_child()
+  if self.perf_profiling_enabled: self.perf_monitor.end_component("_render_discussion_panel")
+
+ def _render_synthesis_panel(self) -> None:
+  """Renders a panel for synthesizing multiple discussion takes."""
+  imgui.text("Select takes to synthesize:")
+  discussions = self.project.get('discussion', {}).get('discussions', {})
+  if not hasattr(self, 'ui_synthesis_selected_takes'):
+   self.ui_synthesis_selected_takes = {name: False for name in discussions}
+  if not hasattr(self, 'ui_synthesis_prompt'):
+   self.ui_synthesis_prompt = ""
+  for name in discussions:
+   _, self.ui_synthesis_selected_takes[name] = imgui.checkbox(name, self.ui_synthesis_selected_takes.get(name, False))
+  imgui.spacing()
+  imgui.text("Synthesis Prompt:")
+  _, self.ui_synthesis_prompt = imgui.input_text_multiline("##synthesis_prompt", self.ui_synthesis_prompt, imgui.ImVec2(-1, 100))
+  if imgui.button("Generate Synthesis"):
+   selected = [name for name, sel in self.ui_synthesis_selected_takes.items() if sel]
+   if len(selected) > 1:
+    from src import synthesis_formatter
+    discussions_dict = self.project.get('discussion', {}).get('discussions', {})
+    takes_dict = {name: discussions_dict.get(name, {}).get('history', []) for name in selected}
+    diff_text = synthesis_formatter.format_takes_diff(takes_dict)
+    prompt = f"{self.ui_synthesis_prompt}\n\nHere are the variations:\n{diff_text}"
+    
+    new_name = "synthesis_take"
+    counter = 1
+    while new_name in discussions_dict:
+     new_name = f"synthesis_take_{counter}"
+     counter += 1
+     
+    self._create_discussion(new_name)
+    with self._disc_entries_lock:
+     self.disc_entries.append({"role": "User", "content": prompt, "collapsed": False, "ts": project_manager.now_ts()})
+    self._handle_generate_send()
 
  def _render_persona_selector_panel(self) -> None:
   if self.perf_profiling_enabled: self.perf_monitor.start_component("_render_persona_selector_panel")
@@ -2314,6 +2652,8 @@ def hello():
    if imgui.selectable("None", not self.ui_active_persona)[0]:
     self.ui_active_persona = ""
    for pname in sorted(personas.keys()):
+    if not pname:
+     continue
     if imgui.selectable(pname, pname == self.ui_active_persona)[0]:
      self.ui_active_persona = pname
      if pname in personas:
@@ -2322,6 +2662,7 @@ def hello():
       self._editing_persona_system_prompt = persona.system_prompt or ""
       self._editing_persona_tool_preset_id = persona.tool_preset or ""
       self._editing_persona_bias_profile_id = persona.bias_profile or ""
+      self._editing_persona_context_preset_id = getattr(persona, 'context_preset', '') or ""
       import copy
       self._editing_persona_preferred_models_list = copy.deepcopy(persona.preferred_models) if persona.preferred_models else []
       self._editing_persona_is_new = False
@@ -2350,6 +2691,9 @@ def hello():
       if persona.bias_profile:
        self.ui_active_bias_profile = persona.bias_profile
        ai_client.set_bias_profile(persona.bias_profile)
+      if getattr(persona, 'context_preset', None):
+       self.ui_active_context_preset = persona.context_preset
+       self.load_context_preset(persona.context_preset)
    imgui.end_combo()
   imgui.same_line()
   if imgui.button("Manage Personas"):
@@ -2730,14 +3074,24 @@ def hello():
   imgui.begin_child("response_scroll_area", imgui.ImVec2(0, -40), True)
   is_nerv = theme.is_nerv_active()
   if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
-  markdown_helper.render(self.ai_response, context_id="response")
+  
+  segments, parsed_response = thinking_parser.parse_thinking_trace(self.ai_response)
+  if segments:
+   self._render_thinking_trace([{"content": s.content, "marker": s.marker} for s in segments], 9999)
+  
+  markdown_helper.render(parsed_response, context_id="response")
+  
   if is_nerv: imgui.pop_style_color()
   imgui.end_child()
   
   imgui.separator()
   if imgui.button("-> History"):
    if self.ai_response:
-    self.disc_entries.append({"role": "AI", "content": self.ai_response, "collapsed": True, "ts": project_manager.now_ts()})
+    segments, response = thinking_parser.parse_thinking_trace(self.ai_response)
+    entry = {"role": "AI", "content": response, "collapsed": True, "ts": project_manager.now_ts()}
+    if segments:
+     entry["thinking_segments"] = [{"content": s.content, "marker": s.marker} for s in segments]
+    self.disc_entries.append(entry)
   if is_blinking:
    imgui.pop_style_color(2)
   if self.perf_profiling_enabled: self.perf_monitor.end_component("_render_response_panel")
@@ -2853,6 +3207,12 @@ def hello():
     imgui.text_colored(C_LBL, f"#{i_display}")
     imgui.same_line()
     imgui.text_colored(vec4(160, 160, 160), ts)
+    
+    latency = entry.get("latency") or entry.get("metadata", {}).get("latency")
+    if latency:
+     imgui.same_line()
+     imgui.text_colored(C_SUB, f" ({latency:.2f}s)")
+
     ticket_id = entry.get("mma_ticket_id")
     if ticket_id:
      imgui.same_line()
@@ -2871,14 +3231,34 @@ def hello():
     # Optimized content rendering using _render_heavy_text logic
     idx_str = str(i)
     if kind == "request":
+     usage = payload.get("usage", {})
+     if usage:
+      inp = usage.get("input_tokens", 0)
+      imgui.text_colored(C_LBL, f" tokens in:{inp}")
      self._render_heavy_text("message", payload.get("message", ""), idx_str)
      if payload.get("system"):
       self._render_heavy_text("system", payload.get("system", ""), idx_str)
     elif kind == "response":
      r = payload.get("round", 0)
      sr = payload.get("stop_reason", "STOP")
-     imgui.text_colored(C_LBL, f"round: {r} stop_reason: {sr}")
-     self._render_heavy_text("text", payload.get("text", ""), idx_str)
+     usage = payload.get("usage", {})
+     usage_str = ""
+     if usage:
+      inp = usage.get("input_tokens", 0)
+      out = usage.get("output_tokens", 0)
+      cache = usage.get("cache_read_input_tokens", 0)
+      usage_str = f" in:{inp} out:{out}"
+      if cache:
+       usage_str += f" cache:{cache}"
+     imgui.text_colored(C_LBL, f"round: {r} stop_reason: {sr}{usage_str}")
+     
+     text_content = payload.get("text", "")
+     segments, parsed_response = thinking_parser.parse_thinking_trace(text_content)
+     if segments:
+      self._render_thinking_trace([{"content": s.content, "marker": s.marker} for s in segments], i, is_standalone=not bool(parsed_response.strip()))
+     if parsed_response:
+      self._render_heavy_text("text", parsed_response, idx_str)
+     
      tcs = payload.get("tool_calls", [])
      if tcs:
       self._render_heavy_text("tool_calls", json.dumps(tcs, indent=1), idx_str)
@@ -2938,7 +3318,7 @@ def hello():
      script = entry.get("script", "")
      res = entry.get("result", "")
      # Use a clear, formatted combined view for the detail window
-     combined = f"COMMAND:\n{script}\n\n{'='*40}\nOUTPUT:\n{res}"
+     combined = f"**COMMAND:**\n```powershell\n{script}\n```\n\n---\n**OUTPUT:**\n```text\n{res}\n```"
      
      script_preview = script.replace("\n", " ")[:150]
      if len(script) > 150: script_preview += "..."
@@ -2946,6 +3326,7 @@ def hello():
      if imgui.is_item_clicked():
       self.text_viewer_title = f"Tool Call #{i+1} Details"
       self.text_viewer_content = combined
+      self.text_viewer_type = 'markdown'
       self.show_text_viewer = True
      
      imgui.table_next_column()
@@ -2955,6 +3336,7 @@ def hello():
      if imgui.is_item_clicked():
       self.text_viewer_title = f"Tool Call #{i+1} Details"
       self.text_viewer_content = combined
+      self.text_viewer_type = 'markdown'
       self.show_text_viewer = True
       
    imgui.end_table()
@@ -3175,6 +3557,24 @@ def hello():
 
  def _render_mma_dashboard(self) -> None:
   if self.perf_profiling_enabled: self.perf_monitor.start_component("_render_mma_dashboard")
+  
+  # Focus Agent dropdown
+  imgui.text("Focus Agent:")
+  imgui.same_line()
+  focus_label = self.ui_focus_agent or "All"
+  if imgui.begin_combo("##focus_agent", focus_label, imgui.ComboFlags_.width_fit_preview):
+   if imgui.selectable("All", self.ui_focus_agent is None)[0]:
+    self.ui_focus_agent = None
+   for tier in ["Tier 2", "Tier 3", "Tier 4"]:
+    if imgui.selectable(tier, self.ui_focus_agent == tier)[0]:
+     self.ui_focus_agent = tier
+   imgui.end_combo()
+  imgui.same_line()
+  if self.ui_focus_agent:
+   if imgui.button("x##clear_focus"):
+    self.ui_focus_agent = None
+  imgui.separator()
+
   is_nerv = theme.is_nerv_active()
   if self.is_viewing_prior_session:
    c = vec4(255, 200, 100)
@@ -3821,6 +4221,8 @@ def hello():
      from src import ai_client
      ai_client.set_bias_profile(None)
     for bname in sorted(self.controller.bias_profiles.keys()):
+     if not bname:
+      continue
      if imgui.selectable(bname, bname == getattr(self, 'ui_active_bias_profile', ""))[0]:
       self.ui_active_bias_profile = bname
       from src import ai_client

src/models.py

@@ -111,6 +111,7 @@ DEFAULT_TOOL_CATEGORIES: Dict[str, List[str]] = {
 
 def parse_history_entries(history_strings: list[str], roles: list[str]) -> list[dict[str, Any]]:
  import re
+ from src import thinking_parser
  entries = []
  for raw in history_strings:
   ts = ""
@@ -128,11 +129,30 @@ def parse_history_entries(history_strings: list[str], roles: list[str]) -> list[
    content = rest[match.end():].strip()
   else:
    content = rest
-  entries.append({"role": role, "content": content, "collapsed": True, "ts": ts})
+   
+  entry_obj = {"role": role, "content": content, "collapsed": True, "ts": ts}
+  if role == "AI" and ("<thinking>" in content or "<thought>" in content or "Thinking:" in content):
+   segments, parsed_content = thinking_parser.parse_thinking_trace(content)
+   if segments:
+    entry_obj["content"] = parsed_content
+    entry_obj["thinking_segments"] = [{"content": s.content, "marker": s.marker} for s in segments]
+    
+  entries.append(entry_obj)
  return entries
 
 @dataclass
-@dataclass
+class ThinkingSegment:
+ content: str
+ marker: str # 'thinking', 'thought', or 'Thinking:'
+
+ def to_dict(self) -> Dict[str, Any]:
+  return {"content": self.content, "marker": self.marker}
+
+ @classmethod
+ def from_dict(cls, data: Dict[str, Any]) -> "ThinkingSegment":
+  return cls(content=data["content"], marker=data["marker"])
+
+
 @dataclass
 class Ticket:
  id: str
@@ -239,8 +259,6 @@ class Track:
   )
 
 
-@dataclass
-@dataclass
 @dataclass
 class WorkerContext:
  ticket_id: str
@@ -339,12 +357,14 @@ class FileItem:
  path: str
  auto_aggregate: bool = True
  force_full: bool = False
+ injected_at: Optional[float] = None
 
  def to_dict(self) -> Dict[str, Any]:
   return {
    "path": self.path,
    "auto_aggregate": self.auto_aggregate,
    "force_full": self.force_full,
+   "injected_at": self.injected_at,
   }
 
  @classmethod
@@ -353,6 +373,7 @@ class FileItem:
    path=data["path"],
    auto_aggregate=data.get("auto_aggregate", True),
    force_full=data.get("force_full", False),
+   injected_at=data.get("injected_at"),
   )
 
 @dataclass
@@ -448,6 +469,7 @@ class Persona:
  system_prompt: str = ''
  tool_preset: Optional[str] = None
  bias_profile: Optional[str] = None
+ context_preset: Optional[str] = None
 
  @property
  def provider(self) -> Optional[str]:
@@ -490,6 +512,8 @@ class Persona:
    res["tool_preset"] = self.tool_preset
   if self.bias_profile is not None:
    res["bias_profile"] = self.bias_profile
+  if self.context_preset is not None:
+   res["context_preset"] = self.context_preset
   return res
 
  @classmethod
@@ -523,8 +547,8 @@ class Persona:
    system_prompt=data.get("system_prompt", ""),
    tool_preset=data.get("tool_preset"),
    bias_profile=data.get("bias_profile"),
+   context_preset=data.get("context_preset"),
   )
-
 @dataclass
 class MCPServerConfig:
  name: str

src/project_manager.py

@@ -33,6 +33,14 @@ def entry_to_str(entry: dict[str, Any]) -> str:
  ts = entry.get("ts", "")
  role = entry.get("role", "User")
  content = entry.get("content", "")
+ 
+ segments = entry.get("thinking_segments")
+ if segments:
+  for s in segments:
+   marker = s.get("marker", "thinking")
+   s_content = s.get("content", "")
+   content = f"<{marker}>\n{s_content}\n</{marker}>\n{content}"
+   
  if ts:
   return f"@{ts}\n{role}:\n{content}"
  return f"{role}:\n{content}"
@@ -93,6 +101,7 @@ def default_project(name: str = "unnamed") -> dict[str, Any]:
   "output":      {"output_dir": "./md_gen"},
   "files":       {"base_dir": ".", "paths": [], "tier_assignments": {}},
   "screenshots": {"base_dir": ".", "paths": []},
+  "context_presets": {},
   "gemini_cli":  {"binary_path": "gemini"},
   "deepseek":    {"reasoning_effort": "medium"},
   "agent":       {
@@ -235,11 +244,33 @@ def flat_config(proj: dict[str, Any], disc_name: Optional[str] = None, track_id:
   "output":          proj.get("output", {}),
   "files":           proj.get("files",  {}),
   "screenshots":     proj.get("screenshots", {}),
+  "context_presets": proj.get("context_presets", {}),
   "discussion":      {
    "roles":   disc_sec.get("roles", []),
    "history": history,
   },
  }
+ # ── context presets ──────────────────────────────────────────────────────────
+
+def save_context_preset(project_dict: dict, preset_name: str, files: list[str], screenshots: list[str]) -> None:
+ """Save a named context preset (files + screenshots) into the project dict."""
+ if "context_presets" not in project_dict:
+  project_dict["context_presets"] = {}
+ project_dict["context_presets"][preset_name] = {
+  "files": files,
+  "screenshots": screenshots
+ }
+
+def load_context_preset(project_dict: dict, preset_name: str) -> dict:
+ """Return the files and screenshots for a named preset."""
+ if "context_presets" not in project_dict or preset_name not in project_dict["context_presets"]:
+  raise KeyError(f"Preset '{preset_name}' not found in project context_presets.")
+ return project_dict["context_presets"][preset_name]
+
+def delete_context_preset(project_dict: dict, preset_name: str) -> None:
+ """Remove a named preset if it exists."""
+ if "context_presets" in project_dict:
+  project_dict["context_presets"].pop(preset_name, None)
  # ── track state persistence ─────────────────────────────────────────────────
 
 def save_track_state(track_id: str, state: 'TrackState', base_dir: Union[str, Path] = ".") -> None:
@@ -393,3 +424,36 @@ def calculate_track_progress(tickets: list) -> dict:
   "todo": todo
  }
 
+
+def branch_discussion(project_dict: dict, source_id: str, new_id: str, message_index: int) -> None:
+ """
+ Creates a new discussion in project_dict['discussion']['discussions'] by copying 
+ the history from source_id up to (and including) message_index, and sets active to new_id.
+ """
+ if "discussion" not in project_dict or "discussions" not in project_dict["discussion"]:
+  return
+ if source_id not in project_dict["discussion"]["discussions"]:
+  return
+ 
+ source_disc = project_dict["discussion"]["discussions"][source_id]
+ new_disc = default_discussion()
+ new_disc["git_commit"] = source_disc.get("git_commit", "")
+ # Copy history up to and including message_index
+ new_disc["history"] = source_disc["history"][:message_index + 1]
+ 
+ project_dict["discussion"]["discussions"][new_id] = new_disc
+ project_dict["discussion"]["active"] = new_id
+
+def promote_take(project_dict: dict, take_id: str, new_id: str) -> None:
+ """Renames a take_id to new_id in the discussions dict."""
+ if "discussion" not in project_dict or "discussions" not in project_dict["discussion"]:
+  return
+ if take_id not in project_dict["discussion"]["discussions"]:
+  return
+ 
+ disc = project_dict["discussion"]["discussions"].pop(take_id)
+ project_dict["discussion"]["discussions"][new_id] = disc
+ 
+ # If the take was active, update the active pointer
+ if project_dict["discussion"].get("active") == take_id:
+  project_dict["discussion"]["active"] = new_id

src/synthesis_formatter.py

@@ -0,0 +1,42 @@
+def format_takes_diff(takes: dict[str, list[dict]]) -> str:
+ if not takes:
+  return ""
+ 
+ histories = list(takes.values())
+ if not histories:
+  return ""
+
+ min_len = min(len(h) for h in histories)
+ common_prefix_len = 0
+ for i in range(min_len):
+  first_msg = histories[0][i]
+  if all(h[i] == first_msg for h in histories):
+   common_prefix_len += 1
+  else:
+   break
+
+ shared_lines = []
+ for i in range(common_prefix_len):
+  msg = histories[0][i]
+  shared_lines.append(f"{msg.get('role', 'unknown')}: {msg.get('content', '')}")
+ 
+ shared_text = "=== Shared History ==="
+ if shared_lines:
+  shared_text += "\n" + "\n".join(shared_lines)
+
+ variation_lines = []
+ if len(takes) > 1:
+  for take_name, history in takes.items():
+   if len(history) > common_prefix_len:
+    variation_lines.append(f"[{take_name}]")
+    for i in range(common_prefix_len, len(history)):
+     msg = history[i]
+     variation_lines.append(f"{msg.get('role', 'unknown')}: {msg.get('content', '')}")
+    variation_lines.append("")
+ else:
+  # Single take case
+  pass
+
+ variations_text = "=== Variations ===\n" + "\n".join(variation_lines)
+
+ return shared_text + "\n\n" + variations_text

src/thinking_parser.py

@@ -0,0 +1,53 @@
+import re
+from typing import List, Tuple
+from src.models import ThinkingSegment
+
+def parse_thinking_trace(text: str) -> Tuple[List[ThinkingSegment], str]:
+ """
+ Parses thinking segments from text and returns (segments, response_content).
+ Support extraction of thinking traces from <thinking>...</thinking>, <thought>...</thought>,
+ and blocks prefixed with Thinking:.
+ """
+ segments = []
+ 
+ # 1. Extract <thinking> and <thought> tags
+ current_text = text
+ 
+ # Combined pattern for tags
+ tag_pattern = re.compile(r'<(thinking|thought)>(.*?)</\1>', re.DOTALL | re.IGNORECASE)
+ 
+ def extract_tags(txt: str) -> Tuple[List[ThinkingSegment], str]:
+  found_segments = []
+  
+  def replace_func(match):
+   marker = match.group(1).lower()
+   content = match.group(2).strip()
+   found_segments.append(ThinkingSegment(content=content, marker=marker))
+   return ""
+  
+  remaining = tag_pattern.sub(replace_func, txt)
+  return found_segments, remaining
+
+ tag_segments, remaining = extract_tags(current_text)
+ segments.extend(tag_segments)
+ 
+ # 2. Extract Thinking: prefix
+ # This usually appears at the start of a block and ends with a double newline or a response marker.
+ thinking_colon_pattern = re.compile(r'(?:^|\n)Thinking:\s*(.*?)(?:\n\n|\nResponse:|\nAnswer:|$)', re.DOTALL | re.IGNORECASE)
+ 
+ def extract_colon_blocks(txt: str) -> Tuple[List[ThinkingSegment], str]:
+  found_segments = []
+  
+  def replace_func(match):
+   content = match.group(1).strip()
+   if content:
+    found_segments.append(ThinkingSegment(content=content, marker="Thinking:"))
+   return "\n\n"
+  
+  res = thinking_colon_pattern.sub(replace_func, txt)
+  return found_segments, res
+
+ colon_segments, final_remaining = extract_colon_blocks(remaining)
+ segments.extend(colon_segments)
+ 
+ return segments, final_remaining.strip()

tests/test_context_presets.py

@@ -0,0 +1,59 @@
+import pytest
+from src.project_manager import (
+ save_context_preset,
+ load_context_preset,
+ delete_context_preset
+)
+
+def test_save_context_preset():
+ project_dict = {}
+ preset_name = "test_preset"
+ files = ["file1.py", "file2.py"]
+ screenshots = ["screenshot1.png"]
+ 
+ save_context_preset(project_dict, preset_name, files, screenshots)
+ 
+ assert "context_presets" in project_dict
+ assert preset_name in project_dict["context_presets"]
+ assert project_dict["context_presets"][preset_name]["files"] == files
+ assert project_dict["context_presets"][preset_name]["screenshots"] == screenshots
+
+def test_load_context_preset():
+ project_dict = {
+  "context_presets": {
+   "test_preset": {
+    "files": ["file1.py"],
+    "screenshots": ["screenshot1.png"]
+   }
+  }
+ }
+ 
+ preset = load_context_preset(project_dict, "test_preset")
+ 
+ assert preset["files"] == ["file1.py"]
+ assert preset["screenshots"] == ["screenshot1.png"]
+
+def test_load_nonexistent_preset():
+ project_dict = {"context_presets": {}}
+ with pytest.raises(KeyError):
+  load_context_preset(project_dict, "nonexistent")
+
+def test_delete_context_preset():
+ project_dict = {
+  "context_presets": {
+   "test_preset": {
+    "files": ["file1.py"],
+    "screenshots": []
+   }
+  }
+ }
+ 
+ delete_context_preset(project_dict, "test_preset")
+ 
+ assert "test_preset" not in project_dict["context_presets"]
+
+def test_delete_nonexistent_preset_no_error():
+ project_dict = {"context_presets": {}}
+ # Should not raise error if it doesn't exist
+ delete_context_preset(project_dict, "nonexistent")
+ assert "nonexistent" not in project_dict["context_presets"]

tests/test_discussion_takes.py

@@ -0,0 +1,50 @@
+import unittest
+from src import project_manager
+
+class TestDiscussionTakes(unittest.TestCase):
+ def setUp(self):
+  self.project_dict = project_manager.default_project("test_branching")
+  # Populate initial history in 'main'
+  self.project_dict["discussion"]["discussions"]["main"]["history"] = [
+   "User: Message 0",
+   "AI: Response 0",
+   "User: Message 1",
+   "AI: Response 1",
+   "User: Message 2"
+  ]
+
+ def test_branch_discussion_creates_new_take(self):
+  """Verify that branch_discussion copies history up to index and sets active."""
+  source_id = "main"
+  new_id = "take_1"
+  message_index = 1
+  
+  # This will fail with AttributeError until implemented in project_manager.py
+  project_manager.branch_discussion(self.project_dict, source_id, new_id, message_index)
+  
+  # Asserts
+  self.assertIn(new_id, self.project_dict["discussion"]["discussions"])
+  new_history = self.project_dict["discussion"]["discussions"][new_id]["history"]
+  self.assertEqual(len(new_history), 2)
+  self.assertEqual(new_history[0], "User: Message 0")
+  self.assertEqual(new_history[1], "AI: Response 0")
+  self.assertEqual(self.project_dict["discussion"]["active"], new_id)
+
+ def test_promote_take_renames_discussion(self):
+  """Verify that promote_take renames a discussion key."""
+  take_id = "take_experimental"
+  self.project_dict["discussion"]["discussions"][take_id] = project_manager.default_discussion()
+  self.project_dict["discussion"]["discussions"][take_id]["history"] = ["User: Experimental"]
+  
+  new_id = "feature_refined"
+  
+  # This will fail with AttributeError until implemented in project_manager.py
+  project_manager.promote_take(self.project_dict, take_id, new_id)
+  
+  # Asserts
+  self.assertNotIn(take_id, self.project_dict["discussion"]["discussions"])
+  self.assertIn(new_id, self.project_dict["discussion"]["discussions"])
+  self.assertEqual(self.project_dict["discussion"]["discussions"][new_id]["history"], ["User: Experimental"])
+
+if __name__ == "__main__":
+ unittest.main()

tests/test_discussion_takes_gui.py

@@ -0,0 +1,96 @@
+import pytest
+from unittest.mock import MagicMock, patch, call
+from src.gui_2 import App
+
+@pytest.fixture
+def app_instance():
+ with (
+  patch('src.models.load_config', return_value={'ai': {'provider': 'gemini', 'model': 'gemini-2.5-flash-lite'}, 'projects': {}}),
+  patch('src.models.save_config'),
+  patch('src.gui_2.project_manager'),
+  patch('src.gui_2.session_logger'),
+  patch('src.gui_2.immapp.run'),
+  patch('src.app_controller.AppController._load_active_project'),
+  patch('src.app_controller.AppController._fetch_models'),
+  patch.object(App, '_load_fonts'),
+  patch.object(App, '_post_init'),
+  patch('src.app_controller.AppController._prune_old_logs'),
+  patch('src.app_controller.AppController.start_services'),
+  patch('src.api_hooks.HookServer'),
+  patch('src.ai_client.set_provider'),
+  patch('src.ai_client.reset_session')
+ ):
+  app = App()
+  # Setup project discussions
+  app.project = {
+   "discussion": {
+    "active": "main",
+    "discussions": {
+     "main": {"history": []},
+     "take_1": {"history": []},
+     "take_2": {"history": []}
+    }
+   }
+  }
+  app.active_discussion = "main"
+  app.is_viewing_prior_session = False
+  app.ui_disc_new_name_input = ""
+  app.ui_disc_truncate_pairs = 1
+  yield app
+
+def test_render_discussion_tabs(app_instance):
+ """Verify that _render_discussion_panel uses tabs for discussions."""
+ with patch('src.gui_2.imgui') as mock_imgui:
+  # Setup defaults for common imgui calls to avoid unpacking errors
+  mock_imgui.collapsing_header.return_value = True
+  mock_imgui.begin_combo.return_value = False
+  mock_imgui.input_text.return_value = (False, "")
+  mock_imgui.input_int.return_value = (False, 0)
+  mock_imgui.button.return_value = False
+  mock_imgui.checkbox.return_value = (False, False)
+  mock_imgui.begin_child.return_value = True
+  mock_imgui.selectable.return_value = (False, False)
+  
+  # Mock tab bar calls
+  mock_imgui.begin_tab_bar.return_value = True
+  mock_imgui.begin_tab_item.return_value = (False, False)
+
+  app_instance._render_discussion_panel()
+
+  # Check if begin_tab_bar was called
+  # This SHOULD fail if it's not implemented yet
+  mock_imgui.begin_tab_bar.assert_called_with("##discussion_tabs")
+  
+  # Check if begin_tab_item was called for each discussion
+  names = sorted(["main", "take_1", "take_2"])
+  for name in names:
+   mock_imgui.begin_tab_item.assert_any_call(name)
+
+def test_switching_discussion_via_tabs(app_instance):
+ """Verify that clicking a tab switches the discussion."""
+ with patch('src.gui_2.imgui') as mock_imgui, \
+      patch('src.app_controller.AppController._switch_discussion') as mock_switch:
+  # Setup defaults
+  mock_imgui.collapsing_header.return_value = True
+  mock_imgui.begin_combo.return_value = False
+  mock_imgui.input_text.return_value = (False, "")
+  mock_imgui.input_int.return_value = (False, 0)
+  mock_imgui.button.return_value = False
+  mock_imgui.checkbox.return_value = (False, False)
+  mock_imgui.begin_child.return_value = True
+  mock_imgui.selectable.return_value = (False, False)
+
+  mock_imgui.begin_tab_bar.return_value = True
+  
+  # Simulate 'take_1' being active/selected
+  def side_effect(name, flags=None):
+   if name == "take_1":
+    return (True, True)
+   return (False, True)
+  
+  mock_imgui.begin_tab_item.side_effect = side_effect
+  
+  app_instance._render_discussion_panel()
+  
+  # If implemented with tabs, this should be called
+  mock_switch.assert_called_with("take_1")

tests/test_file_item_model.py

@@ -7,6 +7,7 @@ def test_file_item_fields():
  assert item.path == "src/models.py"
  assert item.auto_aggregate is True
  assert item.force_full is False
+ assert item.injected_at is None
 
 def test_file_item_to_dict():
  """Test that FileItem can be serialized to a dict."""
@@ -14,7 +15,8 @@ def test_file_item_to_dict():
  expected = {
   "path": "test.py",
   "auto_aggregate": False,
-  "force_full": True
+  "force_full": True,
+  "injected_at": None
  }
  assert item.to_dict() == expected
 
@@ -23,12 +25,14 @@ def test_file_item_from_dict():
  data = {
   "path": "test.py",
   "auto_aggregate": False,
-  "force_full": True
+  "force_full": True,
+  "injected_at": 123.456
  }
  item = FileItem.from_dict(data)
  assert item.path == "test.py"
  assert item.auto_aggregate is False
  assert item.force_full is True
+ assert item.injected_at == 123.456
 
 def test_file_item_from_dict_defaults():
  """Test that FileItem.from_dict handles missing fields."""
@@ -37,3 +41,4 @@ def test_file_item_from_dict_defaults():
  assert item.path == "test.py"
  assert item.auto_aggregate is True
  assert item.force_full is False
+ assert item.injected_at is None

tests/test_gui_context_presets.py

@@ -0,0 +1,35 @@
+import pytest
+import time
+from src.api_hook_client import ApiHookClient
+
+def test_gui_context_preset_save_load(live_gui) -> None:
+ """Verify that saving and loading context presets works via the GUI app."""
+ client = ApiHookClient()
+ assert client.wait_for_server(timeout=15)
+
+ preset_name = "test_gui_preset"
+ test_files = ["test.py"]
+ test_screenshots = ["test.png"]
+
+ client.push_event("custom_callback", {"callback": "simulate_save_preset", "args": [preset_name]})
+ time.sleep(1.5)
+
+ project_data = client.get_project()
+ project = project_data.get("project", {})
+ presets = project.get("context_presets", {})
+ 
+ assert preset_name in presets, f"Preset '{preset_name}' not found in project context_presets"
+ 
+ preset_entry = presets[preset_name]
+ preset_files = [f["path"] if isinstance(f, dict) else str(f) for f in preset_entry.get("files", [])]
+ assert preset_files == test_files
+ assert preset_entry.get("screenshots", []) == test_screenshots
+
+ # Load the preset
+ client.push_event("custom_callback", {"callback": "load_context_preset", "args": [preset_name]})
+ time.sleep(1.0)
+
+ context = client.get_context_state()
+ loaded_files = [f["path"] if isinstance(f, dict) else str(f) for f in context.get("files", [])]
+ assert loaded_files == test_files
+ assert context.get("screenshots", []) == test_screenshots

tests/test_gui_discussion_tabs.py

@@ -0,0 +1,53 @@
+import pytest
+from unittest.mock import patch, MagicMock, PropertyMock
+
+from src import gui_2
+
+@pytest.fixture
+def mock_gui():
+    gui = gui_2.App()
+    gui.project = {
+        'discussion': {
+            'active': 'main',
+            'discussions': {
+                'main': {'history': []},
+                'main_take_1': {'history': []},
+                'other_topic': {'history': []}
+            }
+        }
+    }
+    gui.active_discussion = 'main'
+    gui.perf_profiling_enabled = False
+    gui.is_viewing_prior_session = False
+    gui._get_discussion_names = lambda: ['main', 'main_take_1', 'other_topic']
+    return gui
+
+def test_discussion_tabs_rendered(mock_gui):
+    with patch('src.gui_2.imgui') as mock_imgui, \
+         patch('src.app_controller.AppController.active_project_root', new_callable=PropertyMock, return_value='.'):
+        
+        # We expect a combo box for base discussion
+        mock_imgui.begin_combo.return_value = True
+        mock_imgui.selectable.return_value = (False, False)
+        
+        # We expect a tab bar for takes
+        mock_imgui.begin_tab_bar.return_value = True
+        mock_imgui.begin_tab_item.return_value = (True, True)
+        mock_imgui.input_text.return_value = (False, "")
+        mock_imgui.input_text_multiline.return_value = (False, "")
+        mock_imgui.checkbox.return_value = (False, False)
+        mock_imgui.input_int.return_value = (False, 0)
+        
+        mock_clipper = MagicMock()
+        mock_clipper.step.return_value = False
+        mock_imgui.ListClipper.return_value = mock_clipper
+        
+        mock_gui._render_discussion_panel()
+        
+        mock_imgui.begin_combo.assert_called_once_with("##disc_sel", 'main')
+        mock_imgui.begin_tab_bar.assert_called_once_with('discussion_takes_tabs')
+        
+        calls = [c[0][0] for c in mock_imgui.begin_tab_item.call_args_list]
+        assert 'Original###main' in calls
+        assert 'Take 1###main_take_1' in calls
+        assert 'Synthesis###Synthesis' in calls

tests/test_gui_phase4.py

@@ -91,6 +91,7 @@ def test_track_discussion_toggle(mock_app: App):
   mock_imgui.button.return_value = False
   mock_imgui.collapsing_header.return_value = True # For Discussions header
   mock_imgui.input_text.side_effect = lambda label, value, *args, **kwargs: (False, value)
+  mock_imgui.input_text_multiline.side_effect = lambda label, value, *args, **kwargs: (False, value)
   mock_imgui.input_int.side_effect = lambda label, value, *args, **kwargs: (False, value)
   mock_imgui.begin_child.return_value = True
   # Mock clipper to avoid the while loop hang

tests/test_gui_symbol_navigation.py

@@ -8,7 +8,8 @@ def test_render_discussion_panel_symbol_lookup(mock_app, role):
  with (
   patch('src.gui_2.imgui') as mock_imgui,
   patch('src.gui_2.mcp_client') as mock_mcp,
-  patch('src.gui_2.project_manager') as mock_pm
+  patch('src.gui_2.project_manager') as mock_pm,
+  patch('src.markdown_helper.imgui_md') as mock_md
  ):
   # Set up App instance state
   mock_app.perf_profiling_enabled = False

tests/test_gui_synthesis.py

@@ -0,0 +1,56 @@
+import pytest
+from unittest.mock import MagicMock, patch, ANY
+from src.gui_2 import App
+
+@pytest.fixture
+def app_instance():
+ with (
+  patch('src.models.load_config', return_value={'ai': {'provider': 'gemini', 'model': 'gemini-2.5-flash-lite'}, 'projects': {}}),
+  patch('src.models.save_config'),
+  patch('src.gui_2.project_manager'),
+  patch('src.gui_2.session_logger'),
+  patch('src.gui_2.immapp.run'),
+  patch('src.app_controller.AppController._load_active_project'),
+  patch('src.app_controller.AppController._fetch_models'),
+  patch.object(App, '_load_fonts'),
+  patch.object(App, '_post_init'),
+  patch('src.app_controller.AppController._prune_old_logs'),
+  patch('src.app_controller.AppController.start_services'),
+  patch('src.api_hooks.HookServer'),
+  patch('src.ai_client.set_provider'),
+  patch('src.ai_client.reset_session')
+ ):
+  app = App()
+  app.project = {
+   "discussion": {
+    "active": "main",
+    "discussions": {
+     "main": {"history": []},
+     "take_1": {"history": []},
+     "take_2": {"history": []}
+    }
+   }
+  }
+  app.ui_synthesis_prompt = "Summarize these takes"
+  yield app
+
+def test_render_synthesis_panel(app_instance):
+ """Verify that _render_synthesis_panel renders checkboxes for takes and input for prompt."""
+ with patch('src.gui_2.imgui') as mock_imgui:
+  mock_imgui.checkbox.return_value = (False, False)
+  mock_imgui.input_text_multiline.return_value = (False, app_instance.ui_synthesis_prompt)
+  mock_imgui.button.return_value = False
+
+  # Call the method we are testing
+  app_instance._render_synthesis_panel()
+
+  # 1. Assert imgui.checkbox is called for each take in project_dict['discussion']['discussions']
+  discussions = app_instance.project['discussion']['discussions']
+  for name in discussions:
+   mock_imgui.checkbox.assert_any_call(name, ANY)
+
+  # 2. Assert imgui.input_text_multiline is called for the prompt
+  mock_imgui.input_text_multiline.assert_called_with("##synthesis_prompt", app_instance.ui_synthesis_prompt, ANY)
+
+  # 3. Assert imgui.button is called for 'Generate Synthesis'
+  mock_imgui.button.assert_any_call("Generate Synthesis")

tests/test_gui_text_viewer.py

@@ -0,0 +1,28 @@
+import pytest
+import time
+from src.api_hook_client import ApiHookClient
+
+def test_text_viewer_state_update(live_gui) -> None:
+ """
+ Verifies that we can set text viewer state and it is reflected in GUI state.
+ """
+ client = ApiHookClient()
+ label = "Test Viewer Label"
+ content = "This is test content for the viewer."
+ text_type = "markdown"
+
+ # Add a task to push a custom callback that mutates the app state
+ def set_viewer_state(app):
+  app.show_text_viewer = True
+  app.text_viewer_title = label
+  app.text_viewer_content = content
+  app.text_viewer_type = text_type
+
+ client.push_event("custom_callback", {"callback": set_viewer_state})
+ time.sleep(0.5)
+ 
+ state = client.get_gui_state()
+ assert state is not None
+ assert state.get('show_text_viewer') == True
+ assert state.get('text_viewer_title') == label
+ assert state.get('text_viewer_type') == text_type

tests/test_mma_approval_indicators.py

@@ -5,7 +5,7 @@ from src.gui_2 import App
 
 
 def _make_app(**kwargs):
- app = MagicMock(spec=App)
+ app = MagicMock()
  app.mma_streams = kwargs.get("mma_streams", {})
  app.mma_tier_usage = kwargs.get("mma_tier_usage", {
   "Tier 1": {"input": 0, "output": 0, "model": "gemini-3.1-pro-preview"},
@@ -13,6 +13,7 @@ def _make_app(**kwargs):
   "Tier 3": {"input": 0, "output": 0, "model": "gemini-2.5-flash-lite"},
   "Tier 4": {"input": 0, "output": 0, "model": "gemini-2.5-flash-lite"},
  })
+ app.ui_focus_agent = kwargs.get("ui_focus_agent", None)
  app.tracks = kwargs.get("tracks", [])
  app.active_track = kwargs.get("active_track", None)
  app.active_tickets = kwargs.get("active_tickets", [])

tests/test_synthesis_formatter.py

@@ -0,0 +1,59 @@
+import pytest
+from src.synthesis_formatter import format_takes_diff
+
+def test_format_takes_diff_empty():
+ assert format_takes_diff({}) == ""
+
+def test_format_takes_diff_single_take():
+ takes = {
+  "take1": [
+   {"role": "user", "content": "hello"},
+   {"role": "assistant", "content": "hi"}
+  ]
+ }
+ expected = "=== Shared History ===\nuser: hello\nassistant: hi\n\n=== Variations ===\n"
+ assert format_takes_diff(takes) == expected
+
+def test_format_takes_diff_common_prefix():
+ takes = {
+  "take1": [
+   {"role": "user", "content": "hello"},
+   {"role": "assistant", "content": "hi"},
+   {"role": "user", "content": "how are you?"},
+   {"role": "assistant", "content": "I am fine."}
+  ],
+  "take2": [
+   {"role": "user", "content": "hello"},
+   {"role": "assistant", "content": "hi"},
+   {"role": "user", "content": "what is the time?"},
+   {"role": "assistant", "content": "It is noon."}
+  ]
+ }
+ expected = (
+  "=== Shared History ===\n"
+  "user: hello\n"
+  "assistant: hi\n\n"
+  "=== Variations ===\n"
+  "[take1]\n"
+  "user: how are you?\n"
+  "assistant: I am fine.\n\n"
+  "[take2]\n"
+  "user: what is the time?\n"
+  "assistant: It is noon.\n"
+ )
+ assert format_takes_diff(takes) == expected
+
+def test_format_takes_diff_no_common_prefix():
+ takes = {
+  "take1": [{"role": "user", "content": "a"}],
+  "take2": [{"role": "user", "content": "b"}]
+ }
+ expected = (
+  "=== Shared History ===\n\n"
+  "=== Variations ===\n"
+  "[take1]\n"
+  "user: a\n\n"
+  "[take2]\n"
+  "user: b\n"
+ )
+ assert format_takes_diff(takes) == expected

tests/test_thinking_gui.py

@@ -0,0 +1,53 @@
+import pytest
+
+
+def test_render_thinking_trace_helper_exists():
+    from src.gui_2 import App
+
+    assert hasattr(App, "_render_thinking_trace"), (
+        "_render_thinking_trace helper should exist in App class"
+    )
+
+
+def test_discussion_entry_with_thinking_segments():
+    entry = {
+        "role": "AI",
+        "content": "Here's my response",
+        "thinking_segments": [
+            {"content": "Let me analyze this step by step...", "marker": "thinking"},
+            {"content": "I should consider edge cases...", "marker": "thought"},
+        ],
+        "ts": "2026-03-13T10:00:00",
+        "collapsed": False,
+    }
+    assert "thinking_segments" in entry
+    assert len(entry["thinking_segments"]) == 2
+
+
+def test_discussion_entry_without_thinking():
+    entry = {
+        "role": "User",
+        "content": "Hello",
+        "ts": "2026-03-13T10:00:00",
+        "collapsed": False,
+    }
+    assert "thinking_segments" not in entry
+
+
+def test_thinking_segment_model_compatibility():
+    from src.models import ThinkingSegment
+
+    segment = ThinkingSegment(content="test", marker="thinking")
+    assert segment.content == "test"
+    assert segment.marker == "thinking"
+    d = segment.to_dict()
+    assert d["content"] == "test"
+    assert d["marker"] == "thinking"
+
+
+if __name__ == "__main__":
+    test_render_thinking_trace_helper_exists()
+    test_discussion_entry_with_thinking_segments()
+    test_discussion_entry_without_thinking()
+    test_thinking_segment_model_compatibility()
+    print("All GUI thinking trace tests passed!")

tests/test_thinking_persistence.py

@@ -0,0 +1,94 @@
+import pytest
+import tempfile
+import os
+from pathlib import Path
+from src import project_manager
+from src.models import ThinkingSegment
+
+
+def test_save_and_load_history_with_thinking_segments():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        project_path = Path(tmpdir) / "test_project"
+        project_path.mkdir()
+
+        project_file = project_path / "test_project.toml"
+        project_file.write_text("[project]\nname = 'test'\n")
+
+        history_data = {
+            "entries": [
+                {
+                    "role": "AI",
+                    "content": "Here's the response",
+                    "thinking_segments": [
+                        {"content": "Let me think about this...", "marker": "thinking"}
+                    ],
+                    "ts": "2026-03-13T10:00:00",
+                    "collapsed": False,
+                },
+                {
+                    "role": "User",
+                    "content": "Hello",
+                    "ts": "2026-03-13T09:00:00",
+                    "collapsed": False,
+                },
+            ]
+        }
+
+        project_manager.save_project(
+            {"project": {"name": "test"}}, project_file, disc_data=history_data
+        )
+
+        loaded = project_manager.load_history(project_file)
+
+        assert "entries" in loaded
+        assert len(loaded["entries"]) == 2
+
+        ai_entry = loaded["entries"][0]
+        assert ai_entry["role"] == "AI"
+        assert ai_entry["content"] == "Here's the response"
+        assert "thinking_segments" in ai_entry
+        assert len(ai_entry["thinking_segments"]) == 1
+        assert (
+            ai_entry["thinking_segments"][0]["content"] == "Let me think about this..."
+        )
+
+        user_entry = loaded["entries"][1]
+        assert user_entry["role"] == "User"
+        assert "thinking_segments" not in user_entry
+
+
+def test_entry_to_str_with_thinking():
+    entry = {
+        "role": "AI",
+        "content": "Response text",
+        "thinking_segments": [{"content": "Thinking...", "marker": "thinking"}],
+        "ts": "2026-03-13T10:00:00",
+    }
+    result = project_manager.entry_to_str(entry)
+    assert "@2026-03-13T10:00:00" in result
+    assert "AI:" in result
+    assert "Response text" in result
+
+
+def test_str_to_entry_with_thinking():
+    raw = "@2026-03-13T10:00:00\nAI:\nResponse text"
+    roles = ["User", "AI", "Vendor API", "System", "Reasoning"]
+    result = project_manager.str_to_entry(raw, roles)
+    assert result["role"] == "AI"
+    assert result["content"] == "Response text"
+    assert "ts" in result
+
+
+def test_clean_nones_removes_thinking():
+    entry = {"role": "AI", "content": "Test", "thinking_segments": None, "ts": None}
+    cleaned = project_manager.clean_nones(entry)
+    assert "thinking_segments" not in cleaned
+    assert "ts" not in cleaned
+
+
+if __name__ == "__main__":
+    test_save_and_load_history_with_thinking_segments()
+    test_entry_to_str_with_thinking()
+    test_str_to_entry_with_thinking()
+    test_clean_nones_removes_thinking()
+    print("All project_manager thinking tests passed!")

tests/test_thinking_trace.py

@@ -0,0 +1,68 @@
+from src.thinking_parser import parse_thinking_trace
+
+
+def test_parse_xml_thinking_tag():
+    raw = "<thinking>\nLet me analyze this problem step by step.\n</thinking>\nHere is the answer."
+    segments, response = parse_thinking_trace(raw)
+    assert len(segments) == 1
+    assert segments[0].content == "Let me analyze this problem step by step."
+    assert segments[0].marker == "thinking"
+    assert response == "Here is the answer."
+
+
+def test_parse_xml_thought_tag():
+    raw = "<thought>This is my reasoning process</thought>\nFinal response here."
+    segments, response = parse_thinking_trace(raw)
+    assert len(segments) == 1
+    assert segments[0].content == "This is my reasoning process"
+    assert segments[0].marker == "thought"
+    assert response == "Final response here."
+
+
+def test_parse_text_thinking_prefix():
+    raw = "Thinking:\nThis is a text-based thinking trace.\n\nNow for the actual response."
+    segments, response = parse_thinking_trace(raw)
+    assert len(segments) == 1
+    assert segments[0].content == "This is a text-based thinking trace."
+    assert segments[0].marker == "Thinking:"
+    assert response == "Now for the actual response."
+
+
+def test_parse_no_thinking():
+    raw = "This is a normal response without any thinking markers."
+    segments, response = parse_thinking_trace(raw)
+    assert len(segments) == 0
+    assert response == raw
+
+
+def test_parse_empty_response():
+    segments, response = parse_thinking_trace("")
+    assert len(segments) == 0
+    assert response == ""
+
+
+def test_parse_multiple_markers():
+    raw = "<thinking>First thinking</thinking>\n<thought>Second thought</thought>\nResponse"
+    segments, response = parse_thinking_trace(raw)
+    assert len(segments) == 2
+    assert segments[0].content == "First thinking"
+    assert segments[1].content == "Second thought"
+
+
+def test_parse_thinking_with_empty_response():
+    raw = "<thinking>Just thinking, no response</thinking>"
+    segments, response = parse_thinking_trace(raw)
+    assert len(segments) == 1
+    assert segments[0].content == "Just thinking, no response"
+    assert response == ""
+
+
+if __name__ == "__main__":
+    test_parse_xml_thinking_tag()
+    test_parse_xml_thought_tag()
+    test_parse_text_thinking_prefix()
+    test_parse_no_thinking()
+    test_parse_empty_response()
+    test_parse_multiple_markers()
+    test_parse_thinking_with_empty_response()
+    print("All thinking trace tests passed!")