…ixes

Add Gemini CLI as the 6th CAO provider with full TUI status detection,
MCP server registration via `gemini mcp add`, and CAO_TERMINAL_ID
forwarding. Includes 57 unit tests (100% coverage), E2E tests, CI
workflow, and provider documentation.

Cross-provider fixes from 14 Ralph verification loops:
- Fix shell injection in Q CLI and Kiro CLI (f-string → shlex.join)
- Fix Gemini CLI exit sending literal "C-d" text (add send_special_key)
- Fix Claude Code missing CAO_TERMINAL_ID forwarding to MCP subprocesses
- Fix constants.py docstring missing Kimi CLI and Gemini CLI
- Remove unused import in gemini_cli.py

Also adds skill-creator and build-cao-provider skills to all 5 tool
directories (.claude, .codex, .gemini, .kimi, .kiro) and adds lessons
learned #10 (shell injection) and #11 (exit key sequences).

598/598 tests passing, black/isort clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…ixes

Add Gemini CLI as the 6th CAO provider with full TUI status detection,
MCP server registration via `gemini mcp add`, and CAO_TERMINAL_ID
forwarding. Includes 57 unit tests (100% coverage), E2E tests, CI
workflow, and provider documentation.

Cross-provider fixes from 14 Ralph verification loops:
- Fix shell injection in Q CLI and Kiro CLI (f-string → shlex.join)
- Fix Gemini CLI exit sending literal "C-d" text (add send_special_key)
- Fix Claude Code missing CAO_TERMINAL_ID forwarding to MCP subprocesses
- Fix constants.py docstring missing Kimi CLI and Gemini CLI
- Remove unused import in gemini_cli.py

Also adds skill-creator and build-cao-provider skills to all 5 tool
directories (.claude, .codex, .gemini, .kimi, .kiro) and adds lessons
learned #10 (shell injection) and #11 (exit key sequences).

598/598 tests passing, black/isort clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…ixes

Add Gemini CLI as the 6th CAO provider with full TUI status detection,
MCP server registration via `gemini mcp add`, and CAO_TERMINAL_ID
forwarding. Includes 57 unit tests (100% coverage), E2E tests, CI
workflow, and provider documentation.

Cross-provider fixes from 14 Ralph verification loops:
- Fix shell injection in Q CLI and Kiro CLI (f-string → shlex.join)
- Fix Gemini CLI exit sending literal "C-d" text (add send_special_key)
- Fix Claude Code missing CAO_TERMINAL_ID forwarding to MCP subprocesses
- Fix constants.py docstring missing Kimi CLI and Gemini CLI
- Remove unused import in gemini_cli.py

Also adds skill-creator and build-cao-provider skills to all 5 tool
directories (.claude, .codex, .gemini, .kimi, .kiro) and adds lessons
learned #10 (shell injection) and #11 (exit key sequences).

598/598 tests passing, black/isort clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…ixes

Add Gemini CLI as the 6th CAO provider with full TUI status detection,
MCP server registration via `gemini mcp add`, and CAO_TERMINAL_ID
forwarding. Includes 57 unit tests (100% coverage), E2E tests, CI
workflow, and provider documentation.

Cross-provider fixes from 14 Ralph verification loops:
- Fix shell injection in Q CLI and Kiro CLI (f-string → shlex.join)
- Fix Gemini CLI exit sending literal "C-d" text (add send_special_key)
- Fix Claude Code missing CAO_TERMINAL_ID forwarding to MCP subprocesses
- Fix constants.py docstring missing Kimi CLI and Gemini CLI
- Remove unused import in gemini_cli.py

Also adds skill-creator and build-cao-provider skills to all 5 tool
directories (.claude, .codex, .gemini, .kimi, .kiro) and adds lessons
learned #10 (shell injection) and #11 (exit key sequences).

598/598 tests passing, black/isort clean.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

- Update analysis_supervisor.md agent profile with "How Message Delivery
  Works" section explaining that messages arrive when the agent is idle,
  and agents must NOT run shell commands to wait (fixes Kimi CLI
  busy-wait blocking inbox delivery)
- Add lesson #17: Proactive Models Block Inbox Delivery by Busy-Waiting
- Fix 10 issues found in skills review:
  - Add Kiro CLI to provider lists (contributed lesson #9)
  - Fix lesson cross-references (#15→#11/#12 for supervisor E2E, #9→#8
    for Ralph)
  - Fix outdated "literal=True" → "bracketed paste" in lesson #10
  - Fix "prompt_toolkit (Kimi CLI, Codex)" → Codex is Rust-native TUI
  - Fix Kimi timeout "restore on cleanup" → NOT restored (concurrent
    instances)
  - Fix init timeout 60s→120s in implementation checklist
  - Add missing supervisor E2E command in Ralph fix_plan.md

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

…l display, status accuracy, Ralph UI

Bug #3: Added AI-Powered Bead Creation with textarea and Generate Beads button
Bug #4: Added Context Monitor showing context usage (Xk ctx) in session cards
Bug #5: Added Model Display showing model name in session cards
Bug #10: Improved status detection in TerminalView with spinner pattern detection
Bug #12: Added Ralph Loop UI with PRD textarea and configuration inputs

All 10 bugs now have implementations.

…(Codex)

Phase 2 Task 9 + TSK-080 follow-up.

terminal_service:
- replaced 14 call sites of tmux_client.<m>(...) with
  get_multiplexer().<m>(...). lru_cache on the accessor keeps repeated
  calls O(1).
- added optional launch_spec: LaunchSpec | None = None to
  create_terminal(); forwards verbatim to multiplexer.create_session()
  and create_window(). Default None preserves all existing callers.
- removes the last runtime-critical hidden-leakage finding from
  TSK-071's audit (#10/awslabs#11 in that report).

Test migration (+ TSK-080 follow-up):
- test_terminal_service.py: switched fixtures to patch get_multiplexer
  accessor seam, added LaunchSpec pass-through coverage.
- test_terminal_service_full.py, test_terminal_service_coverage.py,
  test_plugin_event_emission.py: migrated decorators/setattrs/assertion
  references from .tmux_client to .get_multiplexer (the original Task 9
  prompt missed these three; Codex caught the regression after the
  source change exposed them as +40 failures).

Verified: 43 fail / 1107 pass — same baseline; +24 net new tests pass
since Task 6 baseline.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

…(Codex)

Phase 2 Task 9 + TSK-080 follow-up.

terminal_service:
- replaced 14 call sites of tmux_client.<m>(...) with
  get_multiplexer().<m>(...). lru_cache on the accessor keeps repeated
  calls O(1).
- added optional launch_spec: LaunchSpec | None = None to
  create_terminal(); forwards verbatim to multiplexer.create_session()
  and create_window(). Default None preserves all existing callers.
- removes the last runtime-critical hidden-leakage finding from
  TSK-071's audit (#10/awslabs#11 in that report).

Test migration (+ TSK-080 follow-up):
- test_terminal_service.py: switched fixtures to patch get_multiplexer
  accessor seam, added LaunchSpec pass-through coverage.
- test_terminal_service_full.py, test_terminal_service_coverage.py,
  test_plugin_event_emission.py: migrated decorators/setattrs/assertion
  references from .tmux_client to .get_multiplexer (the original Task 9
  prompt missed these three; Codex caught the regression after the
  source change exposed them as +40 failures).

Verified: 43 fail / 1107 pass — same baseline; +24 net new tests pass
since Task 6 baseline.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>