0d64d8e559
Tracked: morrowind agent (py/cfg), skills/, training-data/, research/, notes/, specs/, test-results/, metrics/, heartbeat/, briefings/, memories/, skins/, hooks/, decisions.md, OPERATIONS.md, SOUL.md Excluded: screenshots, PNGs, binaries, sessions, databases, secrets, audio cache, timmy-config/ and timmy-telemetry/ (separate repos)
12 lines
5.1 KiB
JSON
12 lines
5.1 KiB
JSON
[
|
|
{
|
|
"prompt": "TIME BUDGET: You have 20 minutes for this cycle. Plan accordingly \u2014 do not start work you cannot finish.\n\nPRIORITIZED QUEUE (10 ready issues):\n 1. #486 [REFACTOR] score=9 \u2014 Complete airllm removal from backends, agent, CLI and tests\n files: src/timmy/backends.py, src/timmy/agent.py, src/timmy/tools_intro/__init__.py\n 2. #505 [REFACTOR] score=8 \u2014 Break up self_reflect() \u2014 108 lines in session_logger.py\n files: src/timmy/session_logger.py\n 3. #457 [FEATURE] score=7 \u2014 Provider health history endpoint\n files: tests/infrastructure/test_router_history.py, src/infrastructure/router/history.py, src/infrastructure/router/api.py\n 4. #531 [REFACTOR] score=6 \u2014 Break up run_agentic_loop() \u2014 121 lines in agentic_loop.py\n files: src/timmy/agentic_loop.py\n 5. #532 [REFACTOR] score=6 \u2014 Break up _maybe_file_issues() \u2014 100 lines in thinking.py\n files: src/timmy/thinking.py\n 6. #538 [REFACTOR] score=6 \u2014 Break up git.py::run() \u2014 90 lines\n files: src/infrastructure/hands/git.py\n 7. #539 [REFACTOR] score=6 \u2014 Break up shell.py::run() \u2014 89 lines\n files: src/infrastructure/hands/shell.py\n 8. #540 [REFACTOR] score=6 \u2014 Break up _gather_system_snapshot() \u2014 86 lines in thinking.py\n files: src/timmy/thinking.py\n ... +2 more\n\nPick from the TOP of this queue. Issue #486 is highest priority.\n\nYou are the Timmy development loop orchestrator.\n\nCANONICAL REPO: ~/Timmy-Time-dashboard (SACRED \u2014 do NOT touch, read-only)\nAPI: http://localhost:3000/api/v1/repos/rockachopa/Timmy-time-dashboard\nGITEA TOKEN: ~/.hermes/gitea_token (Timmy user \u2014 admin, NOT ~/.config/gitea/token)\nSTATE: ~/Timmy-Time-dashboard/.loop/state.json\nCLAIMS: ~/Timmy-Time-dashboard/.loop/claims.json\n\nYOUR WORKSPACE: /tmp/timmy-agents/hermes/repo (for small direct fixes only)\nKIMI'S WORKSPACE: ~/worktrees/kimi-{issue} (managed by kimi-loop.sh, hands off)\n\n\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\nRULES\n\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550",
|
|
"chosen": "Starting development loop cycle. Let me assess the current state.",
|
|
"session": "session_20260319_203257_eba637.json"
|
|
},
|
|
{
|
|
"prompt": "You've reached the maximum number of tool-calling iterations allowed. Please provide a final response summarizing what you've found and accomplished so far, without calling any more tools.",
|
|
"chosen": "# Loop Cycle 946 \u2014 Summary\n\n## Completed: Issue #486 (score=9) \u2014 Complete airllm removal\n\n**PR #545** opened and ready for merge: `refactor/remove-airllm`\n\n### What was done\n\nRemoved all airllm/AirLLM dead code across 10 files:\n\n**Source changes:**\n- `backends.py` \u2014 Removed `TimmyAirLLMAgent` class, `airllm_available()`, `_AIRLLM_MODELS` dict, `ModelSize` type alias\n- `agent.py` \u2014 Removed airllm from `_resolve_backend()` auto-detection, removed `model_size` parameter from `create_timmy()`, simplified `TimmyAgent` union type\n- `cli.py` \u2014 Updated `--backend` and `--model-size` help text\n- `tools_intro/__init__.py` \u2014 Updated docstring\n- `__init__.py` \u2014 Updated module docstring\n\n**Test changes:**\n- `conftest.py` \u2014 Removed airllm sys.modules stub\n- `test_agent.py` \u2014 Removed 4+ airllm-specific test functions\n- `test_backends.py` \u2014 Removed all airllm test functions and helpers\n- `test_cli.py` \u2014 Removed airllm CLI test\n- `test_mobile_scenarios.py` \u2014 Removed entire M6xx AirLLM contract test section\n\n### Results\n- **+17 / -553 lines** \u2014 net negative 536 lines deleted\n- **2104 passed**, 42 skipped, 0 failures (full pre-push gate)\n- **Coverage: 78.57%** (above 73% threshold)\n- Only 1 remaining \"airllm\" reference: a historical commit message string in test fixture data (appropriate to keep)\n\n## Status of other queue items\n\nAll top issues (#486, #505, #457, #531, #532, #538, #539) are assigned to Kimi, but Kimi has **0 open PRs** and appears to not be running. Two issues (#540, #541) are unassigned.\n\n## Next cycle actions needed\n1. **Merge PR #545** (all gates green)\n2. **Close #486** after merge\n3. **Investigate Kimi** \u2014 7 issues assigned, 0 output. May need restart or reassignment.\n4. **Take #540 or #541** if Kimi remains idle \u2014 these are small refactors (80-86 lines)\n5. **Unassign stale Kimi issues** if Kimi can't be restarted",
|
|
"session": "session_20260319_203257_eba637.json"
|
|
}
|
|
] |