8e6462d10b
conductor(plan): Mark task 'Task 2.3' as complete
2026-03-02 16:48:13 -05:00
1f92629a55
feat(mcp_client): add MUTATING_TOOLS frozenset sentinel for HITL enforcement
2026-03-02 16:47:51 -05:00
2d8f9f4d7a
conductor(plan): Mark task 'Task 2.2' as complete
2026-03-02 16:47:15 -05:00
4b7338a076
feat(gui): expand AGENT_TOOL_NAMES to all 26 MCP tools with mutating tools grouped
2026-03-02 16:46:56 -05:00
9e86eaf12b
conductor(plan): Mark task 'Task 2.1' as complete
2026-03-02 16:45:57 -05:00
e4ccb065d4
feat(config): expose all 26 MCP tools in toml + default_project; mutating tools off by default
2026-03-02 16:45:34 -05:00
ac4be7eca4
conductor(plan): Mark phase 'Phase 1' as complete
2026-03-02 16:43:17 -05:00
15536d77fc
conductor(checkpoint): Checkpoint end of Phase 1 — meta-tooling token fix + portability
2026-03-02 16:42:56 -05:00
29260ae374
conductor(plan): Mark task 'Task 1.2' as complete
2026-03-02 16:42:28 -05:00
b30f040c7b
fix(mma_exec): remove hardcoded C:\projects\misc\setup_*.ps1 paths — rely on PATH
2026-03-02 16:42:11 -05:00
3322b630c2
conductor(plan): Mark task 'Task 1.1' as complete
2026-03-02 16:38:51 -05:00
687545932a
refactor(mma_exec): remove UNFETTERED_MODULES — all deps use generate_skeleton()
2026-03-02 16:38:28 -05:00
40b50953a1
docs: close mma_agent_focus_ux track; log concurrent-tier + hook-verification backlog items
2026-03-02 16:31:32 -05:00
22b08ef91e
conductor(plan): Mark Phase 3 complete [checkpoint: b30e563]
2026-03-02 16:30:35 -05:00
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
4f77d8fdd9
conductor(plan): Mark Phase 2 complete [checkpoint: 865d8dd]
2026-03-02 16:23:21 -05:00
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
fb0d6be2e6
conductor(plan): Record Phase 1 checkpoint bc1a570; mark Task 2.1 in progress
2026-03-02 16:20:52 -05:00
bc1a5707a0
conductor(checkpoint): Checkpoint end of Phase 1 — mma_agent_focus_ux
2026-03-02 16:20:25 -05:00
00a196cf13
conductor(plan): Mark Phase 1 tasks 1.1-1.6 complete ( 8d9f25d)
2026-03-02 16:19:01 -05:00
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
264b04f060
chore: close feature_bleed_cleanup_20260302 — update TASKS.md and JOURNAL.md
...
All 3 phases complete and verified. 62 lines of dead code removed from gui_2.py.
Meta-Level Sanity Check: 0 new ruff violations introduced.
Next track: mma_agent_focus_ux_20260302 (dependency on Phase 1 now satisfied)
2026-03-02 15:57:16 -05:00
8ea636147e
conductor(plan): Mark phase 'Phase 3 - Token Budget Layout Fix' as complete [ 0d081a2]
2026-03-02 15:55:53 -05:00
0d081a28c5
conductor(checkpoint): Checkpoint end of Phase 3 — feature_bleed_cleanup_20260302
...
Phase 3: Token Budget Layout Fix
- Removed 4 redundant lines from _render_provider_panel (double labels + embedded call)
- Added collapsing_header('Token Budget') to AI Settings after 'System Prompts'
- 32 tests passed, import clean
- Token Budget header verified by user
2026-03-02 15:55:34 -05:00
35abc265e9
conductor(plan): Mark task 3.4 complete — Token Budget collapsing header verified
2026-03-02 15:55:28 -05:00
5180038090
conductor(plan): Mark task 3.3 complete — 32 passed
2026-03-02 15:51:10 -05:00
bd3d0e77db
conductor(plan): Mark tasks 3.1-3.2 complete, begin 3.3 — 6097368
2026-03-02 15:50:27 -05:00
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
97792e7fff
conductor(plan): Mark phase 'Phase 2 - Menu Bar Consolidation' as complete [ 15fd786]
2026-03-02 15:44:11 -05:00
15fd7862b1
conductor(checkpoint): Checkpoint end of Phase 2 — feature_bleed_cleanup_20260302
...
Phase 2: Menu Bar Consolidation
- Deleted dead begin_main_menu_bar() block (24 lines, always-False in HelloImGui)
- Added 'manual slop' > Quit menu to live _show_menus using runner_params.app_shall_exit
- 32 tests passed, import clean
- Quit menu verified by user
2026-03-02 15:43:55 -05:00
b96405aaa3
conductor(plan): Mark task 2.4 complete — Quit menu verified by user
2026-03-02 15:43:47 -05:00
e6e8298025
conductor(plan): Mark task 2.3 complete — 32 passed
2026-03-02 15:42:13 -05:00
acd7c05977
conductor(plan): Mark task 2.2 complete, begin 2.3 — 340f44e
2026-03-02 15:41:34 -05:00
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
cb5f328da3
conductor(plan): Mark task 2.1 complete, begin 2.2 — b0f5a5c
2026-03-02 15:39:41 -05:00
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
129cc33d01
conductor(plan): Mark phase 'Phase 1 - Dead Code Removal' as complete [ be7174c]
2026-03-02 15:35:26 -05:00
be7174ca53
conductor(checkpoint): Checkpoint end of Phase 1 — feature_bleed_cleanup_20260302
...
Phase 1: Dead Code Removal
- Deleted dead _render_comms_history_panel duplicate (33 lines, stale 'type' key)
- Deleted 4 duplicate __init__ state assignments
- 32 tests passed, gui_2.py import clean
- Comms History panel visually verified by user
2026-03-02 15:34:48 -05:00
763bc2e734
conductor(plan): Mark task 1.4 complete — Comms History panel verified visually
2026-03-02 14:32:25 -05:00
10724f86a5
conductor(plan): Mark task 1.3 complete — 32 passed, import ok, 2 pre-existing failures unrelated
2026-03-02 14:29:57 -05:00
535667b51f
conductor(plan): Mark task 1.2 complete — e28f89f
2026-03-02 14:25:15 -05:00
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
21c74772f6
conductor(plan): Mark task 1.1 complete — 2e9c995
2026-03-02 14:23:47 -05:00
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
e72d512372
docs: sync Claude Tier 2 skill with Gemini — add atomic commits and sanity check rules
...
Port two responsibilities from Gemini's mma-tier2-tech-lead SKILL.md (b4de62f , 7afa3f3 )
to Claude's equivalent command file:
- ATOMIC PER-TASK COMMITS: enforce per-task commit discipline
- Meta-Level Sanity Check: ruff + mypy post-track verification
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com >
2026-03-02 14:18:31 -05:00
b9686392d7
chore: apply ruff auto-fixes and remove dead AST scripts
2026-03-02 13:26:20 -05:00
54635d8d1c
docs: append test performance track to backlog based on timeout evaluation
2026-03-02 13:22:45 -05:00
7afa3f3090
docs: Add Meta-Level Sanity Check responsibility to Tier 2 skill
2026-03-02 13:09:36 -05:00
792c96f14f
docs: add strict static analysis and typing track to backlog
2026-03-02 13:08:19 -05:00
f84edf10c7
fix: resolve unterminated string literal in ping_pong simulation
2026-03-02 13:06:40 -05:00