checkpoint: track complete

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).
 
@@ -54,6 +55,8 @@ 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.
+- **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 branching, timestamping, and specific git commit linkage per conversation.
 - **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.

conductor/tracks.md

@@ -35,8 +35,8 @@ 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/)*
+   *Link: [./tracks/thinking_trace_handling_20260313/](./tracks/thinking_trace_handling_20260313/)*
 
 ---
 
@@ -60,14 +60,14 @@ 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**
    *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.*
 
@@ -79,12 +79,9 @@ This file tracks all major tracks for the project. Each track has its own detail
     *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 +161,10 @@ 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/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.
+- [x] Task: Write failing tests for saving, loading, and listing Context Presets in the project configuration. 93a590c
-- [ ] Task: Implement Context Preset storage logic (e.g., updating TOML schemas in `project_manager.py`) to manage file/screenshot lists.
+- [x] Task: Implement Context Preset storage logic (e.g., updating TOML schemas in `project_manager.py`) to manage file/screenshot lists. 93a590c
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: Backend Support for Context Presets' (Protocol in workflow.md)
+- [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.
+- [x] Task: Write tests for the Context Hub UI components handling preset saving and loading. 573f5ee
-- [ ] Task: Implement the UI controls in the Context Hub to save current selections as a preset and load existing presets.
+- [x] Task: Implement the UI controls in the Context Hub to save current selections as a preset and load existing presets. 573f5ee
-- [ ] Task: Update the Persona configuration UI (`personas.py` / `gui_2.py`) to allow assigning a named Context Preset to an agent persona.
+- [x] Task: Update the Persona configuration UI (`personas.py` / `gui_2.py`) to allow assigning a named Context Preset to an agent persona. 791e1b7
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: GUI Integration & Persona Assignment' (Protocol in workflow.md)
+- [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.
+- [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
-- [ ] Task: Implement UI elements in the Session Hub to expose the aggregated markdown and the active system prompt.
+- [x] Task: Implement UI elements in the Session Hub to expose the aggregated markdown and the active system prompt. 84b6266
-- [ ] Task: Enhance the discussion timeline rendering in `gui_2.py` to visually indicate exactly when files and screenshots were injected into the context.
+- [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
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: Transparent Context Visibility' (Protocol in workflow.md)
+- [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.
+- [x] Task: Write tests for the GUI state filtering logic when focusing on a specific agent's session. 038c909
-- [ ] Task: Relocate the 'Focus Agent' feature from the Operations Hub to the MMA Dashboard.
+- [x] Task: Relocate the 'Focus Agent' feature from the Operations Hub to the MMA Dashboard. 038c909
-- [ ] Task: Implement the action to filter the Session and Discussion hubs based on the selected agent's context.
+- [x] Task: Implement the action to filter the Session and Discussion hubs based on the selected agent's context. 038c909
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Agent-Focused Session Filtering' (Protocol in workflow.md)
+- [x] Task: Conductor - User Manual Verification 'Phase 4: Agent-Focused Session Filtering' (Protocol in workflow.md) 038c909

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__`.
+- [x] Task: Audit `src/gui_2.py` to ensure all `text_viewer_*` state variables are explicitly initialized in `App.__init__`. e28af48
-- [ ] 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").
+- [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
-- [ ] Task: Implement: Update `self.text_viewer_wrap` (defaulting to True) to allow independent word wrap.
+- [x] Task: Implement: Update `self.text_viewer_wrap` (defaulting to True) to allow independent word wrap. e28af48
-- [ ] Task: Implement: Update `_render_text_viewer(self, label: str, content: str, text_type: str = "text")` signature and caller usage.
+- [x] Task: Implement: Update `_render_text_viewer(self, label: str, content: str, text_type: str = "text")` signature and caller usage. e28af48
-- [ ] Task: Conductor - User Manual Verification 'Phase 1: State & Interface Update' (Protocol in workflow.md)
+- [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`.
+- [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
-- [ ] Task: Implement: In `src/gui_2.py`, refactor the text viewer window loop to:
+- [x] Task: Implement: In `src/gui_2.py`, refactor the text viewer window loop to: a91b8dc
-  - Use `MarkdownRenderer.render` if `text_type == "markdown"`.
+  - Use `MarkdownRenderer.render` if `text_type == "markdown"`. a91b8dc
-  - Use a cached `ImGuiColorTextEdit.TextEditor` if `text_type` matches a code language.
+  - Use a cached `ImGuiColorTextEdit.TextEditor` if `text_type` matches a code language. a91b8dc
-  - Fallback to `imgui.input_text_multiline` for plain text.
+  - Fallback to `imgui.input_text_multiline` for plain text. a91b8dc
-- [ ] Task: Implement: Ensure the `TextEditor` instance is properly cached using a unique key for the text viewer to maintain state.
+- [x] Task: Implement: Ensure the `TextEditor` instance is properly cached using a unique key for the text viewer to maintain state. a91b8dc
-- [ ] Task: Conductor - User Manual Verification 'Phase 2: Core Rendering Logic' (Protocol in workflow.md)
+- [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.
+- [x] Task: Write Tests: Update `tests/test_gui_text_viewer.py` to verify the copy-to-clipboard functionality and word wrap toggle. a91b8dc
-- [ ] Task: Implement: Add a "Copy" button to the text viewer title bar or a small toolbar at the top of the window.
+- [x] Task: Implement: Add a "Copy" button to the text viewer title bar or a small toolbar at the top of the window. a91b8dc
-- [ ] Task: Implement: Add a "Word Wrap" checkbox inside the text viewer window.
+- [x] Task: Implement: Add a "Word Wrap" checkbox inside the text viewer window. a91b8dc
-- [ ] Task: Implement: Configure the `TextEditor` instance to show line numbers and be read-only.
+- [x] Task: Implement: Configure the `TextEditor` instance to show line numbers and be read-only. a91b8dc
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: UI Features' (Protocol in workflow.md)
+- [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.
+- [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
-- [ ] Task: Implement: Add "Markdown Preview" support for system prompt presets using the new text viewer logic.
+- [x] Task: Implement: Add "Markdown Preview" support for system prompt presets using the new text viewer logic. 2826ad5
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Integration & Rollout' (Protocol in workflow.md)
+- [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
+## Status: COMPLETE (2026-03-14)
-- [ ] 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)
 
-## Phase 2: Persistence & History Integration
+## Summary
-- [ ] Task: Write Tests: Verify that `ProjectManager` correctly serializes and deserializes messages with thinking segments to/from TOML history files.
+Implemented thinking trace parsing, model, persistence, and GUI rendering for AI responses containing `<thinking>`, `<thought>`, and `Thinking:` markers.
-- [ ] 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)
 
-## Phase 3: GUI Rendering - Comms & Discussion
+## Files Created/Modified:
-- [ ] Task: Write Tests: Verify the GUI rendering logic correctly handles messages with and without thinking segments.
+- `src/thinking_parser.py` - Parser for thinking traces
-- [ ] Task: Implement: Create a reusable `_render_thinking_trace` helper in `src/gui_2.py` using a collapsible header (e.g., `imgui.collapsing_header`).
+- `src/models.py` - ThinkingSegment model
-- [ ] Task: Implement: Integrate the thinking trace renderer into the **Comms History** panel in `src/gui_2.py`.
+- `src/gui_2.py` - _render_thinking_trace helper + integration
-- [ ] Task: Implement: Integrate the thinking trace renderer into the **Discussion Hub** message loop in `src/gui_2.py`.
+- `tests/test_thinking_trace.py` - 7 parsing tests
-- [ ] Task: Conductor - User Manual Verification 'Phase 3: GUI Rendering - Comms & Discussion' (Protocol in workflow.md)
+- `tests/test_thinking_persistence.py` - 4 persistence tests  
+- `tests/test_thinking_gui.py` - 4 GUI tests
 
-## Phase 4: Final Polish & Theming
+## Implementation Details:
-- [ ] Task: Implement: Apply specialized styling (e.g., tinted background or italicized text) to expanded thinking traces to distinguish them from direct responses.
+- **Parser**: Extracts thinking segments from `<thinking>`, `<thought>`, `Thinking:` markers
-- [ ] Task: Implement: Ensure thinking trace headers show a "Calculating..." or "Monologue" indicator while an agent is active.
+- **Model**: `ThinkingSegment` dataclass with content and marker fields
-- [ ] Task: Conductor - User Manual Verification 'Phase 4: Final Polish & Theming' (Protocol in workflow.md)
+- **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

@@ -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
@@ -37,7 +37,7 @@ separate_external_tools = false
 "Context Hub" = true
 "Files & Media" = true
 "AI Settings" = true
-"MMA Dashboard" = true
+"MMA Dashboard" = false
 "Task DAG" = false
 "Usage Analytics" = false
 "Tier 1" = false
@@ -54,7 +54,7 @@ Message = false
 Response = true
 "Tool Calls" = false
 Theme = true
-"Log Management" = true
+"Log Management" = false
 Diagnostics = false
 "External Tools" = false
 "Shader Editor" = false
@@ -64,8 +64,8 @@ palette = "Nord Dark"
 font_path = "C:/projects/manual_slop/assets/fonts/MapleMono-Regular.ttf"
 font_size = 18.0
 scale = 1.0
-transparency = 0.5400000214576721
+transparency = 1.0
-child_transparency = 0.5899999737739563
+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
+Pos=1946,1000
-Size=1111,773
+Size=1339,785
 Collapsed=0
 
 [Window][Tool Calls]
-Pos=520,1144
+Pos=1028,1668
-Size=663,232
+Size=1397,340
 Collapsed=0
 DockId=0x00000006,0
 
@@ -74,8 +74,8 @@ Collapsed=0
 DockId=0xAFC85805,2
 
 [Window][Theme]
-Pos=0,703
+Pos=0,1010
-Size=630,737
+Size=828,999
 Collapsed=0
 DockId=0x00000002,2
 
@@ -85,14 +85,14 @@ Size=900,700
 Collapsed=0
 
 [Window][Diagnostics]
-Pos=1649,24
+Pos=2177,26
-Size=580,1284
+Size=1162,1777
 Collapsed=0
-DockId=0x00000010,2
+DockId=0x00000010,0
 
 [Window][Context Hub]
-Pos=0,703
+Pos=0,1010
-Size=630,737
+Size=828,999
 Collapsed=0
 DockId=0x00000002,1
 
@@ -103,26 +103,26 @@ Collapsed=0
 DockId=0x0000000D,0
 
 [Window][Discussion Hub]
-Pos=1263,22
+Pos=1768,26
-Size=709,1418
+Size=1263,1983
 Collapsed=0
 DockId=0x00000013,0
 
 [Window][Operations Hub]
-Pos=632,22
+Pos=830,26
-Size=629,1418
+Size=936,1983
 Collapsed=0
 DockId=0x00000005,0
 
 [Window][Files & Media]
-Pos=0,703
+Pos=0,1010
-Size=630,737
+Size=828,999
 Collapsed=0
 DockId=0x00000002,0
 
 [Window][AI Settings]
-Pos=0,22
+Pos=0,26
-Size=630,679
+Size=828,982
 Collapsed=0
 DockId=0x00000001,0
 
@@ -132,16 +132,16 @@ Size=416,325
 Collapsed=0
 
 [Window][MMA Dashboard]
-Pos=1974,22
+Pos=3360,26
-Size=586,1418
+Size=480,2134
 Collapsed=0
 DockId=0x00000010,0
 
 [Window][Log Management]
-Pos=1974,22
+Pos=3360,26
-Size=586,1418
+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
+Pos=2567,1006
-Size=800,562
+Size=746,548
 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
+Pos=901,1502
-Size=900,340
+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
+Pos=1106,942
-Size=900,700
+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
+Pos=2678,26
-Size=586,269
+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
+Pos=989,778
-Size=900,700
+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
+RefScale=18
-Column 0  Width=48
+Column 0  Width=54
-Column 1  Width=68
+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
+RefScale=18
-Column 0  Width=48
+Column 0  Width=54
-Column 1  Width=72
+Column 1  Width=81
 Column 2  Weight=1.0000
-Column 3  Width=120
+Column 3  Width=135
 
 [Table][0x2C515046,4]
-RefScale=16
+RefScale=18
-Column 0  Width=48
+Column 0  Width=54
 Column 1  Weight=1.0000
-Column 2  Width=118
+Column 2  Width=132
-Column 3  Width=48
+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
+RefScale=18
-Column 0  Width=180
+Column 0  Width=202
-Column 1  Width=120
+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
+RefScale=18
-Column 0  Width=132
+Column 0  Width=148
 Column 1  Weight=1.0000
 
 [Table][0x2C261E6E,2]
-RefScale=16
+RefScale=18
-Column 0  Width=99
+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
+DockSpace           ID=0xAFC85805 Window=0x079D3A04 Pos=0,26 Size=3031,1983 Split=X
-  DockNode          ID=0x00000003 Parent=0xAFC85805 SizeRef=1640,1183 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=0x00000007 Parent=0x0000000B SizeRef=828,858 Split=Y Selected=0x8CA2375C
-        DockNode    ID=0x00000001 Parent=0x00000007 SizeRef=824,525 CentralNode=1 Selected=0x7BD57D6A
+        DockNode    ID=0x00000001 Parent=0x00000007 SizeRef=824,1056 CentralNode=1 Selected=0x7BD57D6A
-        DockNode    ID=0x00000002 Parent=0x00000007 SizeRef=824,737 Selected=0x8CA2375C
+        DockNode    ID=0x00000002 Parent=0x00000007 SizeRef=824,999 Selected=0xF4139CA2
-      DockNode      ID=0x0000000E Parent=0x0000000B SizeRef=1340,858 Split=X Selected=0x418C7449
+      DockNode      ID=0x0000000E Parent=0x0000000B SizeRef=2201,858 Split=X Selected=0x418C7449
-        DockNode    ID=0x00000012 Parent=0x0000000E SizeRef=629,402 Split=Y Selected=0x418C7449
+        DockNode    ID=0x00000012 Parent=0x0000000E SizeRef=936,402 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=1263,402 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=0x00000004 Parent=0xAFC85805 SizeRef=1162,1183 Split=Y Selected=0x3AEC3498
-    DockNode        ID=0x00000010 Parent=0x00000004 SizeRef=1199,1689 Selected=0x2C0206CE
+    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

mock_debug_prompt.txt

@@ -3096,3 +3096,26 @@ PROMPT:
 role: tool
 Here are the results: {"content": "done"}
 ------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+PATH: Epic Initialization — please produce tracks
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please generate the implementation tickets for this track.
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+Please read test.txt
+You are assigned to Ticket T1.
+Task Description: do something
+------------------
+--- MOCK INVOKED ---
+ARGS: ['tests/mock_gemini_cli.py']
+PROMPT:
+role: tool
+Here are the results: {"content": "done"}
+------------------

project_history.toml

@@ -9,5 +9,5 @@ active = "main"
 
 [discussions.main]
 git_commit = ""
-last_updated = "2026-03-12T20:34:43"
+last_updated = "2026-03-14T09:29:30"
 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"]:
+   inp = u.get("input_tokens", u.get("prompt_tokens", 0))
-    if k in u:
+   out = u.get("output_tokens", u.get("completion_tokens", 0))
-     self.session_usage[k] += u.get(k, 0) or 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")
@@ -1490,22 +1503,42 @@ class AppController:
       "ts": entry.get("ts", project_manager.now_ts())
      })
 
-  if kind in ("tool_result", "tool_call"):
+  if kind == "response":
-   role = "Tool" if kind == "tool_result" else "Vendor API"
+   if self.ui_auto_add_history:
-   content = ""
+    role = payload.get("role", "AI")
-   if kind == "tool_result":
+    text_content = payload.get("text", "")
-    content = payload.get("output", "")
+    if text_content.strip():
-   else:
+     segments, parsed_response = thinking_parser.parse_thinking_trace(text_content)
-    content = payload.get("script") or payload.get("args") or payload.get("message", "")
+     entry_obj = {
-    if isinstance(content, dict):
-     content = json.dumps(content, indent=1)
-   with self._pending_history_adds_lock:
-    self._pending_history_adds.append({
       "role": role,
-      "content": f"[{kind.upper().replace('_', ' ')}]\n{content}",
+      "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":
+     content = payload.get("output", "")
+    else:
+     content = payload.get("script") or payload.get("args") or payload.get("message", "")
+     if isinstance(content, dict):
+      content = json.dumps(content, indent=1)
+    with self._pending_history_adds_lock:
+     self._pending_history_adds.append({
+       "role": role,
+       "content": f"[{kind.upper().replace('_', ' ')}]\n{content}",
+       "collapsed": True,
+       "ts": entry.get("ts", project_manager.now_ts())
+      })
   if kind == "history_add":
    payload = entry.get("payload", {})
    with self._pending_history_adds_lock:
@@ -2485,6 +2518,11 @@ 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/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}
-
+  self.shader_uniforms = {'crt': 1.0, 'scanline': 0.5, 'bloom': 0.8}
- def _handle_approve_tool(self, user_data=None) -> None:
+  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:
+ def _render_text_viewer(self, label: str, content: str, text_type: str = 'text', force_open: bool = False) -> None:
-  if imgui.button("[+]##" + str(id(content))):
+  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)
+    imgui.end_child()
    else:
-    markdown_helper.render_code(content, context_id=ctx_id)
+    imgui.input_text_multiline(f"##heavy_text_input_{label}_{id_suffix}", content, imgui.ImVec2(-1, 180), imgui.InputTextFlags_.read_only)
-   imgui.end_child()
   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):
@@ -663,52 +776,37 @@ class App:
     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.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)
+     if ch1: self.show_windows["Tool Calls"] = self.ui_separate_tool_calls_panel
      imgui.same_line()
-     focus_label = self.ui_focus_agent or "All"
+     ch2, self.ui_separate_usage_analytics = imgui.checkbox("Pop Out Usage Analytics", self.ui_separate_usage_analytics)
-     if imgui.begin_combo("##focus_agent", focus_label, imgui.ComboFlags_.width_fit_preview):
+     if ch2: self.show_windows["Usage Analytics"] = self.ui_separate_usage_analytics
-      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:
+     ch3, self.ui_separate_external_tools = imgui.checkbox('Pop Out External Tools', self.ui_separate_external_tools)
-      if imgui.button("x##clear_focus"):
+     if ch3: self.show_windows['External Tools'] = self.ui_separate_external_tools
-       self.ui_focus_agent = None
+     imgui.pop_style_var()
-     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)
-      if ch1: self.show_windows["Tool Calls"] = self.ui_separate_tool_calls_panel
-      imgui.same_line()
-      ch2, self.ui_separate_usage_analytics = imgui.checkbox("Pop Out Usage Analytics", self.ui_separate_usage_analytics)
-      if ch2: self.show_windows["Usage Analytics"] = self.ui_separate_usage_analytics
-      imgui.same_line()
-      ch3, self.ui_separate_external_tools = imgui.checkbox('Pop Out External Tools', self.ui_separate_external_tools)
-      if ch3: self.show_windows['External Tools'] = self.ui_separate_external_tools
-      imgui.pop_style_var()
 
-      show_tc_tab = not self.ui_separate_tool_calls_panel
+     show_tc_tab = not self.ui_separate_tool_calls_panel
-      show_usage_tab = not self.ui_separate_usage_analytics
+     show_usage_tab = not self.ui_separate_usage_analytics
 
-      if imgui.begin_tab_bar("ops_tabs"):
+     if imgui.begin_tab_bar("ops_tabs"):
-       if imgui.begin_tab_item("Comms History")[0]:
+      if imgui.begin_tab_item("Comms History")[0]:
-        self._render_comms_history_panel()
+       self._render_comms_history_panel()
+       imgui.end_tab_item()
+      if show_tc_tab:
+       if imgui.begin_tab_item("Tool Calls")[0]:
+        self._render_tool_calls_panel()
         imgui.end_tab_item()
-       if show_tc_tab:
+      if show_usage_tab:
-        if imgui.begin_tab_item("Tool Calls")[0]:
+       if imgui.begin_tab_item("Usage Analytics")[0]:
-         self._render_tool_calls_panel()
+        self._render_usage_analytics_panel()
-         imgui.end_tab_item()
+        imgui.end_tab_item()
-       if show_usage_tab:
+      if not self.ui_separate_external_tools:
-        if imgui.begin_tab_item("Usage Analytics")[0]:
+       if imgui.begin_tab_item("External Tools")[0]:
-         self._render_usage_analytics_panel()
+        self._render_external_tools_panel()
-         imgui.end_tab_item()
+        imgui.end_tab_item()
-       if not self.ui_separate_external_tools:
+      imgui.end_tab_bar()
-        if imgui.begin_tab_item("External Tools")[0]:
-         self._render_external_tools_panel()
-         imgui.end_tab_item()
-       imgui.end_tab_bar()
     imgui.end()
    
    if self.ui_separate_message_panel and self.show_windows.get("Message", False):
@@ -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:
@@ -959,14 +1059,42 @@ 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
-      imgui.begin_child("tv_wrap", imgui.ImVec2(-1, -1), False)
+     if imgui.button("Copy"):
-      imgui.push_text_wrap_pos(imgui.get_content_region_avail().x)
+      imgui.set_clipboard_text(self.text_viewer_content)
-      imgui.text(self.text_viewer_content)
+     imgui.same_line()
-      imgui.pop_text_wrap_pos()
+     _, 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:
-      imgui.input_text_multiline("##tv_c", self.text_viewer_content, imgui.ImVec2(-1, -1), imgui.InputTextFlags_.read_only)
+      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)
+       imgui.pop_text_wrap_pos()
+       imgui.end_child()
+      else:
+       imgui.input_text_multiline("##tv_c", self.text_viewer_content, imgui.ImVec2(-1, -1), imgui.InputTextFlags_.read_only)
     imgui.end()
    # Inject File Modal
    if getattr(self, "show_inject_modal", False):
@@ -1100,16 +1228,14 @@ 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"):
+    if imgui.button("Pop out MD Preview"):
-     self._prompt_md_preview = not self._prompt_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:
+    _, self._editing_preset_system_prompt = imgui.input_text_multiline("##pcont", self._editing_preset_system_prompt, imgui.ImVec2(-1, rem_y))
-     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()
 
    # Footer Buttons
@@ -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()
@@ -2212,12 +2412,24 @@ def hello():
       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]
+     entry = display_entries[i]
-     imgui.push_id(str(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 "-"):
@@ -2239,6 +2451,22 @@ def hello():
      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"):
@@ -2251,52 +2479,62 @@ def hello():
       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"]
-       pattern = re.compile(r"\[Definition: (.*?) from (.*?) \(line (\d+)\)\](\s+```[\s\S]*?```)?")
+       if content.strip():
-       matches = list(pattern.finditer(content))
+        pattern = re.compile(r"\[Definition: (.*?) from (.*?) \(line (\d+)\)\](\s+```[\s\S]*?```)?")
-       is_nerv = theme.is_nerv_active()
+        matches = list(pattern.finditer(content))
-       if not matches:
+        is_nerv = theme.is_nerv_active()
-        if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
+        if not matches:
-        markdown_helper.render(content, context_id=f'disc_{i}')
-        if is_nerv: imgui.pop_style_color()
-       else:
-        imgui.begin_child(f"read_content_{i}", imgui.ImVec2(0, 150), True)
-        if self.ui_word_wrap: imgui.push_text_wrap_pos(imgui.get_content_region_avail().x)
-        last_idx = 0
-        for m_idx, match in enumerate(matches):
-         before = content[last_idx:match.start()]
-         if before:
-          if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
-          markdown_helper.render(before, context_id=f'disc_{i}_b_{m_idx}')
-          if is_nerv: imgui.pop_style_color()
-         header_text = match.group(0).split("\n")[0].strip()
-         path = match.group(2)
-         code_block = match.group(4)
-         if imgui.collapsing_header(header_text):
-          if imgui.button(f"[Source]##{i}_{match.start()}"):
-           res = mcp_client.read_file(path)
-           if res:
-            self.text_viewer_title = path
-            self.text_viewer_content = res
-            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()
-         last_idx = match.end()
-        after = content[last_idx:]
-        if after:
          if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
-         markdown_helper.render(after, context_id=f'disc_{i}_a')
+         markdown_helper.render(content, context_id=f'disc_{i}')
          if is_nerv: imgui.pop_style_color()
-        if self.ui_word_wrap: imgui.pop_text_wrap_pos()
+        else:
-        imgui.end_child()
+         imgui.begin_child(f"read_content_{i}", imgui.ImVec2(0, 150), True)
+         if self.ui_word_wrap: imgui.push_text_wrap_pos(imgui.get_content_region_avail().x)
+         last_idx = 0
+         for m_idx, match in enumerate(matches):
+          before = content[last_idx:match.start()]
+          if before:
+           if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
+           markdown_helper.render(before, context_id=f'disc_{i}_b_{m_idx}')
+           if is_nerv: imgui.pop_style_color()
+          header_text = match.group(0).split("\n")[0].strip()
+          path = match.group(2)
+          code_block = match.group(4)
+          if imgui.collapsing_header(header_text):
+           if imgui.button(f"[Source]##{i}_{match.start()}"):
+            res = mcp_client.read_file(path)
+            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:
+            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()
+          last_idx = match.end()
+         after = content[last_idx:]
+         if after:
+          if is_nerv: imgui.push_style_color(imgui.Col_.text, vec4(80, 255, 80))
+          markdown_helper.render(after, context_id=f'disc_{i}_a')
+          if is_nerv: imgui.pop_style_color()
+         if self.ui_word_wrap: imgui.pop_text_wrap_pos()
+         imgui.end_child()
       else:
-       ch, entry["content"] = imgui.input_text_multiline("##content", entry["content"], imgui.ImVec2(-1, 150))
+       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:
@@ -2322,6 +2560,7 @@ 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 +2589,9 @@ 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 +2972,24 @@ 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 +3105,12 @@ 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 +3129,34 @@ 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}")
+     usage = payload.get("usage", {})
-     self._render_heavy_text("text", payload.get("text", ""), idx_str)
+     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 +3216,7 @@ 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 +3224,7 @@ 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 +3234,7 @@ 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 +3455,24 @@ 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)

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":       {
@@ -231,15 +240,37 @@ def flat_config(proj: dict[str, Any], disc_name: Optional[str] = None, track_id:
   disc_data = disc_sec.get("discussions", {}).get(name, {})
   history = disc_data.get("history", [])
  return {
-  "project":     proj.get("project", {}),
+  "project":         proj.get("project", {}),
-  "output":      proj.get("output", {}),
+  "output":          proj.get("output", {}),
-  "files":       proj.get("files",  {}),
+  "files":           proj.get("files",  {}),
-  "screenshots": proj.get("screenshots", {}),
+  "screenshots":     proj.get("screenshots", {}),
-  "discussion":  {
+  "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:

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_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_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_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!")