Commit Graph

87 Commits

Author SHA1 Message Date
Ed_
b30e563fc1 feat(mma): Phase 3 — Focus Agent UI + filter logic
- gui_2.__init__: add ui_focus_agent: str | None = None
- _gui_func: Focus Agent combo (All/Tier2/3/4) + clear button above OperationsTabs
- _render_comms_history_panel: filter by ui_focus_agent; show [source_tier] label per entry
- _render_tool_calls_panel: pre-filter with tool_log_filtered; fix missing i=i_minus_one+1; remove stale tuple destructure
- tests: 6 new Phase 3 tests, 18/18 total
2026-03-02 16:26:41 -05:00
Ed_
865d8dd13b feat(mma): Phase 2 — migrate _render_tool_calls_panel to dict access
Replace tuple destructure 'script, result, _ = self._tool_log[i]'
with dict access 'entry = self._tool_log[i]; script = entry[script]; result = entry[result]'
Prerequisite for Phase 3 filter logic.
2026-03-02 16:21:27 -05:00
Ed_
8d9f25d0ce feat(mma): Phase 1 — source_tier tagging at emission
- ai_client: add current_tier module var; stamp source_tier on every _append_comms entry
- multi_agent_conductor: set current_tier='Tier 3' around send(), clear in finally
- conductor_tech_lead: set current_tier='Tier 2' around send(), clear in finally
- gui_2: _on_tool_log captures current_tier; _append_tool_log stores dict with source_tier
- tests: 8 new tests covering current_tier, source_tier in comms, tool log dict format
2026-03-02 16:18:00 -05:00
Ed_
60973680a8 fix(bleed): fix token budget layout — own collapsing header in AI Settings
Phase 3 changes:
- _render_provider_panel: removed 4 redundant lines (2x 'Token Budget' labels,
  separator, embedded _render_token_budget_panel call)
- _gui_func AI Settings: added collapsing_header('Token Budget') section after
  'System Prompts', calling _render_token_budget_panel cleanly
AI Settings now has three independent collapsing sections.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 15:49:51 -05:00
Ed_
340f44e4bf feat(bleed): add working Quit to _show_menus via runner_params.app_shall_exit
Adds 'manual slop' menu before 'Windows' in the live HelloImGui menubar callback.
Quit sets self.runner_params.app_shall_exit = True — the correct HelloImGui API.
Previously the only quit path was the window close button.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 15:41:12 -05:00
Ed_
b0f5a5c8d3 fix(bleed): remove dead begin_main_menu_bar() block from _gui_func (lines 1674-1697)
HelloImGui commits the menubar before invoking _gui_func, so begin_main_menu_bar()
always returned False. The 24-line block (Quit, View, Project menus) never executed.
Also removes the misaligned '# ---- Menubar' comment and dead '# --- Hubs ---' comment.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 15:39:19 -05:00
Ed_
e28f89f313 fix(bleed): remove duplicate __init__ state assignments (lines 308-311)
ui_conductor_setup_summary, ui_new_track_name, ui_new_track_desc, ui_new_track_type
were each assigned twice in __init__. Second assignments (308-311) were identical
to the correct first assignments (218-221). Duplicate removed, first assignments kept.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 14:24:57 -05:00
Ed_
2e9c995bbe fix(bleed): remove dead duplicate _render_comms_history_panel (lines 3040-3073)
Dead version used stale 'type' key (current model uses 'kind'), called nonexistent
_cb_load_prior_log (correct name: cb_load_prior_log), and had begin_child('scroll_area')
ID collision. Python silently discarded it at import time. Live version at line 3400.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-02 14:23:26 -05:00
Ed_
b9686392d7 chore: apply ruff auto-fixes and remove dead AST scripts 2026-03-02 13:26:20 -05:00
Ed_
6f18102863 feat(token-viz): Phase 3 — auto-refresh triggers and /api/gui/token_stats endpoint 2026-03-02 11:27:00 -05:00
Ed_
7b5d9b1212 feat(token-viz): Phase 2 — trim warning, Gemini/Anthropic cache status display 2026-03-02 11:23:57 -05:00
Ed_
1c8b094a77 fix(gui): restore missing _render_message_panel method def after set_file_slice edit 2026-03-02 11:22:03 -05:00
Ed_
5bfb20f06f feat(token-viz): Phase 1 — token budget panel with color bar and breakdown table 2026-03-02 11:16:32 -05:00
Ed_
57efca4f9b fix(thread-safety): lock disc_entries reads/writes in HookServer, remove debug logs 2026-03-02 10:37:33 -05:00
Ed_
fc9634fd73 fix(gui): move lock init before use, protect disc_entries with threading lock 2026-03-02 10:15:20 -05:00
Ed_
9fb01ce5d1 feat(mma): complete Phase 6 and finalize Comprehensive GUI UX track
- Implement Live Worker Streaming: wire ai_client.comms_log_callback to Tier 3 streams
- Add Parallel DAG Execution using asyncio.gather for non-dependent tickets
- Implement Automatic Retry with Model Escalation (Flash-Lite -> Flash -> Pro)
- Add Tier Model Configuration UI to MMA Dashboard with project TOML persistence
- Fix FPS reporting in PerformanceMonitor to prevent transient 0.0 values
- Update Ticket model with retry_count and dictionary-like access
- Stabilize Gemini CLI integration tests and handle script approval events in simulations
- Finalize and verify all 6 phases of the implementation plan
2026-03-01 22:38:43 -05:00
Ed_
d1ce0eaaeb feat(gui): implement Phases 2-5 of Comprehensive GUI UX track
- Add cost tracking with new cost_tracker.py module
- Enhance Track Proposal modal with editable titles and goals
- Add Conductor Setup summary and New Track creation form to MMA Dashboard
- Implement Task DAG editing (add/delete tickets) and track-scoped discussion
- Add visual polish: color-coded statuses, tinted progress bars, and node indicators
- Support live worker streaming from AI providers to GUI panels
- Fix numerous integration test regressions and stabilize headless service
2026-03-01 20:17:31 -05:00
Ed_
2ce7a87069 feat(gui): Tier stream panels as separate dockable windows (Tier 1-4) 2026-03-01 15:57:46 -05:00
Ed_
8e57ae1247 feat(gui): Add blinking APPROVAL PENDING badge to MMA dashboard 2026-03-01 15:49:18 -05:00
Ed_
3a68243d88 feat(gui): Replace single strategy box with 4-tier collapsible stream panels 2026-03-01 15:28:35 -05:00
Ed_
90fc38f671 fix(sim): wire btn_approve_script and expose pending_script_approval in hook API
_handle_approve_script existed but was not registered in the click handler dict.
_pending_dialog (PowerShell confirmation) was invisible to the hook API —
only _pending_ask_dialog (MCP tool ask) was exposed.

- gui_2.py: register btn_approve_script -> _handle_approve_script
- api_hooks.py: add pending_script_approval field to mma_status response
- visual_sim_mma_v2.py: _drain_approvals handles pending_script_approval

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-03-01 14:31:32 -05:00
Ed_
a2097f14b3 fix(mma): Add Tier 1 and Tier 2 token tracking from comms log
Task 2.2 of mma_pipeline_fix_20260301: _cb_plan_epic captures comms baseline before generate_tracks() and pushes mma_tier_usage['Tier 1'] update via custom_callback. _start_track_logic does same for generate_tickets() -> mma_tier_usage['Tier 2'].
2026-03-01 13:25:07 -05:00
Ed_
6326546005 feat(taxonomy): Redirect logs and artifacts to dedicated sub-folders 2026-03-01 09:03:02 -05:00
Ed_
da21ed543d fix(mma): Unblock visual simulation - event routing, loop passing, adapter preservation
Three independent root causes fixed:
- gui_2.py: Route mma_spawn_approval/mma_step_approval events in _process_event_queue
- multi_agent_conductor.py: Pass asyncio loop from ConductorEngine.run() through to
  thread-pool workers for thread-safe event queue access; add _queue_put helper
- ai_client.py: Preserve GeminiCliAdapter in reset_session() instead of nulling it

Test: visual_sim_mma_v2::test_mma_complete_lifecycle passes in ~8s

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-03-01 08:32:31 -05:00
Ed_
6b0823ad6c checkpoint: this is a mess... need to define stricter DSL or system for how the AI devices sims and hookup api for tests. 2026-02-28 22:50:14 -05:00
Ed_
397b4e6001 chore(mma): Clean up mma_exec.py and robustify visual simulation mocking 2026-02-28 22:27:17 -05:00
Ed_
42c42985ee chore(mma): Verify track loading in visual simulation and fix deterministic ID logic 2026-02-28 22:12:57 -05:00
Ed_
37df4c8003 chore(mma): Deterministic track IDs, worker spawn hooks, and improved simulation reliability 2026-02-28 22:09:18 -05:00
Ed_
ed56e56a2c chore(mma): Checkpoint progress on visual simulation and UI refresh before sub-agent delegation 2026-02-28 21:41:46 -05:00
Ed_
d65fa79e26 chore(mma): Implement visual simulation for Epic planning and fix UI refresh 2026-02-28 21:07:46 -05:00
Ed_
da7a2e35c0 fix(conductor): Apply review suggestions for track 'python_style_refactor_20260227' 2026-02-28 20:53:03 -05:00
Ed_
173ea96fb4 refactor(indentation): Apply codebase-wide 1-space ultra-compact refactor. Formatted 21 core modules and tests. 2026-02-28 19:36:38 -05:00
Ed_
c816f65665 refactor(types): add strict type hints to gui_2.py and gui_legacy.py
Automated pipeline applied 217 type annotations across both UI modules:
- 158 auto -> None return types via AST single-pass
- 25 manual signatures (callbacks, factory methods, complex returns)
- 34 variable type annotations (constants, color tuples, config)

Zero untyped functions/variables remain in either file.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
2026-02-28 11:01:01 -05:00
Ed_
d36632c21a checkpoint: massive refactor 2026-02-28 09:06:45 -05:00
Ed_
25b72fba7e feat(ui): Support multiple concurrent AI response streams and strategy visualization 2026-02-27 22:56:40 -05:00
Ed_
7252d759ef feat(ui): Implement Task DAG Visualizer using ImGui tree nodes 2026-02-27 22:51:55 -05:00
Ed_
2b1cfbb34d feat(ui): Implement Track Browser and progress visualization in MMA Dashboard 2026-02-27 22:49:03 -05:00
Ed_
21157f92c3 feat(mma): Finalize Approval UX Modal in GUI 2026-02-27 22:30:55 -05:00
Ed_
4c53ca11da feat(mma): Implement interception logic in GUI and Conductor 2026-02-27 22:29:55 -05:00
Ed_
6548ce6496 fix(conductor): Apply review suggestions for track 'mma_data_architecture_dag_engine' 2026-02-27 20:20:01 -05:00
Ed_
b845b89543 feat(mma): Implement track-scoped history and optimized sub-agent toolsets 2026-02-27 19:51:13 -05:00
Ed_
3b2d82ed0d feat(mma): Finalize Orchestrator Integration and fix all regressions 2026-02-27 18:31:14 -05:00
Ed_
d087a20f7b checkpoint: mma_orchestrator track 2026-02-26 22:59:26 -05:00
Ed_
716d8b4e13 chore(conductor): Archive completed track 'MMA Core Engine Implementation' 2026-02-26 22:02:33 -05:00
Ed_
332fc4d774 feat(mma): Complete Phase 7 implementation: MMA Dashboard, HITL Step Modal, and Memory Mutator 2026-02-26 21:48:41 -05:00
Ed_
63a82e0d15 feat(mma): Implement MMA Dashboard, Event Handling, and Step Approval Modal in gui_2.py 2026-02-26 21:46:05 -05:00
Ed_
8bb72e351d chore(conductor): Mark track 'MMA Core Engine Implementation' as complete and verify with Phase 6 tests 2026-02-26 21:34:28 -05:00
Ed_
68861c0744 feat(mma): Decouple UI from API calls using UserRequestEvent and AsyncEventQueue 2026-02-26 20:45:23 -05:00
Ed_
fb3da4de36 feat(mma): Integrate Tier 4 QA analysis across all providers and conductor 2026-02-26 20:29:34 -05:00
Ed_
9e56245091 feat(conductor): Restore mma_implementation track 2026-02-26 13:13:29 -05:00