2026-03-06 - 2026-04-06
Overview
2 Releases published by 2 users
Published
GoldenRockachopa
Published
hermes/v0.1
442 Pull requests merged by 8 users
Merged
#1469 [loop-cycle-1] refactor: split dispatcher.py into dispatch/ package (#1450)
Merged
#1468 [loop-cycle-2388] perf: optimize cascade router memory (#1376)
Merged
#1467 [loop-cycle-2386] perf: optimize sovereignty loop performance (#1431)
Merged
#1466 [loop-cycle-38] docs: create IMPLEMENTATION.md tracking SOUL.md compliance (#1387)
Merged
#1465 [loop-cycle-37] chore: add SOUL.md at repo root (#1442)
Merged
#1464 [kimi] Fix triage_score.py to merge queue instead of overwrite (#1463)
Merged
#1461 [kimi] Split scorecard_service.py into focused modules (#1406)
Merged
#1458 [loop-cycle-7] refactor: split research.py into research/ subpackage (#1405)
Merged
#1457 [kimi] Implement graceful shutdown and health checks (#1397)
Merged
#1456 [loop-cycle-5] refactor: split voice_loop.py into voice/ subpackage (#1379)
Merged
#1455 [loop-cycle-3] refactor: split app.py into schedulers.py and startup.py (#1363)
Merged
#1449 [loop-cycle-2] refactor: split world.py into focused submodules (#1360)
Merged
#1448 [loop-cycle-1] refactor: split cascade.py into focused modules (#1342)
Merged
#1438 [loop-cycle-31] fix: create missing kimi-loop.sh script with efficient Gitea filtering (#1415)
Merged
#1359 [loop-cycle-7] fix: Configure mypy with explicit-package-bases for proper src/ layout (#1346)
Merged
#1358 [kimi] Add unit tests for memory/crud.py (#1344)
Merged
#1356 [kimi] Fix: stub cv2 in tests to prevent timeout (#1336)
Merged
#1354 [claude] Add unit tests for tools/system_tools.py (#1345)
Merged
#1355 [loop-cycle-1] fix: thread timeout method for xdist compatibility (#1336)
Merged
#1353 [claude] fix: restore live timestamp to HotMemory.read() (#1339)
Merged
#1352 [claude] Add unit tests for spark/engine.py (#1343)
Merged
#1348 [perplexity] feat: Nexus v2 — Cognitive Awareness & Introspection Engine (#1090)
Merged
#1350 [claude] Placeholder research artifact for issue #1341
Merged
#1347 [kimi] Add comprehensive unit tests for models/budget.py (#1316)
Merged
#1338 [claude] Homepage value proposition — 10-second clarity (#809)
Merged
#1337 [claude] Fix Timmy OFFLINE status & GPU error handling (#811)
Merged
#1335 [claude] SEO foundation — meta tags, sitemap, robots.txt, JSON-LD (#813)
Merged
#1334 [claude] Legal Foundation — ToS, Privacy Policy, Risk Disclaimers (#815)
Merged
#1331 [perplexity] feat: Sovereignty Loop core framework — auto-crystallizer, graduation test, orchestration (#953)
Merged
#1332 [claude] Fix syntax errors in test_llm_triage.py (#1329)
Merged
#1328 [loop-cycle-2112] chore: remove unused imports
Merged
#1327 [claude] SOUL.md Framework — template, authoring guide, versioning (#854)
Merged
#1325 [claude] Timmy Nostr identity — keypair, profile, relay presence (#856)
Merged
#1323 [loop-cycle-1] refactor: split memory_system.py into submodules (#1277)
Merged
#1326 [gemini] feat: automated backlog triage via LLM (#1018)
Merged
#1324 [claude] Mumble voice bridge — Alexander ↔ Timmy co-play audio (#858)
Merged
#1322 [gemini] feat: Add button to update ollama models (#1014)
Merged
#1321 [claude] TES3MP server hardening — multi-player stability & anti-grief (#860)
Merged
#1320 [claude] Add unit tests for scorecard_service.py (#1139)
Merged
#1319 [claude] Real-time monitoring dashboard for all agent systems (#862)
Merged
#1317 [claude] ThreeJS world adapter from Kimi world analysis (#870)
Merged
#1318 [claude] Automated Episode Compiler — Highlights to Published Video (#880)
Merged
#1313 [claude] Fix kimi_delegation unit tests — all 53 pass (#1260)
Merged
#1311 [claude] Add unit tests for orchestration_loop.py (#1278)
Merged
#1310 [claude] feat: enforce 3-issue cap on Kimi delegation (#1304)
Merged
#1307 [claude] Add unit tests for backlog_triage.py (#1293)
Merged
#1308 [claude] Add unit tests for research_tools.py (#1294)
Merged
#1309 [claude] Add unit tests for quest_system.py (#1292)
Merged
#1306 [claude] Split thinking.py into focused sub-modules (#1279)
Merged
#1305 [claude] DeerFlow evaluation research note (#1283)
Merged
#1303 [claude] Add unit tests for kimi_delegation.py (#1295)
Merged
#1302 [claude] Add module docstrings to 9 undocumented files (#1296)
Merged
#1301 [kimi] Add unit tests for sovereignty/perception_cache.py (#1261)
Merged
#1297 [claude] Three-tier model router: Local 8B / Hermes 70B / Cloud API cascade (#882)
Merged
#1299 [claude] feat: SearXNG + Crawl4AI self-hosted search backend (#1282)
Merged
#1298 [claude] Document and validate AirLLM Apple Silicon requirements (#1284)
Merged
#1291 [claude] Implement graceful degradation test scenarios (#919)
Merged
#1290 [loop-cycle-1] docs: add docstrings to VoiceTTS public methods (#774)
Merged
#1288 [claude] Fix empty commits: require git add before commit in Kimi workflow (#1268)
Merged
#1289 [claude] Add unit tests for events system backbone (#917)
Merged
#1273 [claude] Wire delegate_task to DistributedWorker for actual execution (#985)
Merged
#1286 [claude] Research summary: Kimi creative blueprint (#891)
Merged
#1287 [claude] Screenshot dump triage — 5 issues created (#1275)
Merged
#1280 [claude] Integrate health snapshot into Daily Run pre-flight (#923)
Merged
#1276 [claude] Dashboard: Agent Scorecards panel in Mission Control (#929)
Merged
#1274 [claude] Autonomous research pipeline — orchestrator + SOVEREIGNTY.md (#972)
Merged
#1269 [claude] Agent Self-Correction Dashboard (#1007)
Merged
#1263 [claude] feat: Session Sovereignty Report Generator (#957) v3
Merged
#1270 [claude] Restore self-modification loop (#983)
Merged
#1271 [claude] Run 5-test benchmark suite against local model candidates (#1066)
Merged
#1266 [claude] Investigate: document paths to resolution for 5 closed PRs (#1219)
Merged
#1267 [claude] feat: Agent Energy Budget Monitoring (#1009)
Merged
#1257 [loop-cycle-1] fix: ruff format error on test_autoresearch.py (#1256)
Merged
#1255 fix: remove unused variable in test_loop_guard_seed (ruff F841)
Merged
#1254 [loop-cycle] fix: three-strike route test isolation for xdist
Merged
#1253 [claude] Fix cycle-metrics pipeline: seed issue= from queue so retro is never null (#1250)
Merged
#1252 [claude] Autoresearch H1: Apple Silicon support + M3 Max baseline doc (#905)
Merged
#1251 [claude] Fix ImportError: memory_write missing from memory_system (#1249)
Merged
#1248 [claude] Fix pre-existing ruff lint errors blocking git hooks (#1247)
Merged
#1245 [claude] Fix 10 vassal tests flaky under xdist parallel execution (#1243)
Merged
#1244 [kimi] Refactor autoresearch.py -> SystemExperiment class (#906)
Merged
#1240 [claude] Add timmy learn autoresearch entry point (#907)
Merged
#1241 [kimi] Add unit tests for paperclip.py (#1236)
Merged
#1239 [claude] Add unit tests for research_tools.py (#1237)
Merged
#1233 [claude] Qwen3 two-model routing via task complexity classifier (#1065) v2
Merged
#1232 [claude] Three-Strike Detector (#962) v2
Merged
#1230 [claude] ADR-024: canonical Nostr identity in timmy-nostr (#1223)
Merged
#1228 [claude] Gitea activity & branch audit across all repos (#1210)
Merged
#1229 [claude] Rescue unmerged work: open PRs for 3 abandoned branches (#1218)
Merged
#1227 [gemini] Implement semantic index for research outputs (#976)
Merged
#1222 [claude] Enforce one-agent-per-issue via labels, document auto-delete branches (#1220)
Merged
#1221 [claude] refactor: break up monolithic tools.py into a tools/ package (#1215)
Merged
#1216 [claude] Add unit tests for vassal/orchestration_loop.py (#1214)
Merged
#1211 [claude] feat: Nexus — persistent conversational awareness space with live memory (#1208)
Merged
#1209 [loop-cycle] fix: remove unused imports and fix formatting (lint)
Merged
#1207 [loop-cycle] fix: test_config hardcoded ollama model vs .env override
Merged
#1205 [claude] Add offline message queue for Workshop panel (#913)
Merged
#1206 [loop-cycle-3] fix: isolate unit tests from local .env and real Gitea API
Merged
#1204 [loop-cycle] refactor: break up git.py::run() into helpers (#538)
Merged
#1203 [claude] Add unit tests for agent_health.py (#1195)
Merged
#1200 [claude] Add unit tests for vassal/dispatch.py (#1193)
Merged
#1201 [claude] test: improve event bus unit test coverage to 99% (#1191)
Merged
#1198 [claude] Add unit tests for chat_store.py (#1192)
Merged
#1199 [claude] Add unit tests for daily_run.py (#1186)
Merged
#1196 [claude] refactor: break up produce_system_status() (#1194)
Merged
#1190 [claude] refactor: break up cascade.py complete() (#1185)
Merged
#1189 [kimi] Refactor cli.py::daily_run() — 105 lines → 33 lines (#1168)
Merged
#1188 [claude] refactor: break up dispatch_issue() into helpers (#1187)
Merged
#1184 [kimi] Break up dispatch_task() into helper functions (#1137)
Merged
#1182 [claude] Grant kimi write permission for PR creation (#1181)
Merged
#1183 [kimi] Break up _dispatch_via_gitea() into helper functions (#1136)
Merged
#1178 [claude] Fix GITEA_API default to VPS address (#1177)
Merged
#1173 [claude] Refactor thinking.py::_maybe_file_issues() into focused helpers (#1170)
Merged
#1174 [claude] Refactor timmyctl inbox() into helper functions (#1169)
Merged
#1175 [claude] Add unit tests for src/config.py (#1172)
Merged
#1167 [gemini] Docs: Acknowledge The Sovereignty Loop governing architecture (#953)
Merged
#1166 [loop-cycle] refactor: add docstrings to 20 undocumented classes (#1130)
Merged
#1165 [claude] Fix ruff S105/S106/B017/E402 errors in bannerlord (#1161)
Merged
#1164 [claude] Sovereignty metrics emitter + SQLite store (#954)
Merged
#1160 [claude] Implement three-tier metabolic LLM router (#966)
Merged
#1159 [claude] Bannerlord M0: Run cognitive benchmark on hermes3, fix L1 string-int coercion (#1092)
Merged
#1158 [loop-cycle-5] feat: implement 4 TODO stubs in timmyctl/cli.py (#1128)
Merged
#1155 [claude] Bannerlord M3: Full Campaign Strategy — Economy, Diplomacy, Kingdom (#1095)
Merged
#1153 [claude] Fix 27 ruff lint errors blocking all pushes (#1149)
Merged
#1154 [gemini] feat: add Sovereignty Loop architecture document (#953)
Merged
#1152 [kimi] Refactor scorecards.py — break up oversized functions (#1127)
Merged
#1151 [claude] Mark setup script tests as skip_ci (#931)
Merged
#1150 [claude] Add unit tests for cascade.py (#1138)
Merged
#1147 [claude] Break up _build_gitea_tools() into per-operation helpers (#1134)
Merged
#1148 [claude] Break up MCPBridge.run() into helper methods (#1135)
Merged
#1146 [claude] feat: Agent Voice Customization UI (#1017)
Merged
#1144 [claude] Add agent emotional state simulation (#1013)
Merged
#1133 [claude] Hermes health monitor — system resources + model management (#1073)
Merged
#1140 [gemini] feat: add coverage and duration strictness to pytest (#934)
Merged
#1143 [claude] Qwen3 two-model strategy: 14B primary + 8B fast router (#1063)
Merged
#1142 [claude] Vassal Protocol — Timmy as autonomous orchestrator (#1070)
Merged
#1141 [claude] Build Timmy autonomous backlog triage loop (#1071)
Merged
#1132 [gemini] refactor: Gracefully handle tool registration errors (#938)
Merged
#1123 [claude] Build agent dispatcher — route tasks to Claude Code, Kimi, APIs (#1072)
Merged
#1131 [claude] Separate tox unit and integration environments (#933)
Merged
#1124 [claude] Bannerlord M1 — GABS Observer Mode (Passive Lord) (#1093)
Merged
#1125 [gemini] Close branch for issue #1016 (Issue already resolved)
Merged
#1122 [claude] Load fine-tuned Timmy model into Hermes harness (#1104)
Merged
#1119 [gemini] feat: Add Claude API fallback tier to cascade.py (#980)
Merged
#1118 [claude] Implement AutoLoRA continuous improvement loop (#1105)
Merged
#1117 [claude] LoRA trajectory export and fine-tune launcher (#1103)
Merged
#1116 [claude] Bannerlord VM setup guide + GABS connectivity test (#1098)
Merged
#1115 [claude] Fix Starlette 1.0.0 TemplateResponse API in calm and tools routes (#1112)
Merged
#1113 [claude] Wire QuotaMonitor.select_model() into cascade router (#1106)
Merged
#1111 [gemini] feat: Integrate ResearchOrchestrator with Paperclip (#978)
Merged
#1110 [claude] Add Hermes 4 14B Modelfile, providers config, and smoke test (#1101)
Merged
#1109 [claude] Decline out-of-scope Bannerlord M4 formation commander (#1096)
Merged
#1108 [claude] Feudal multi-agent hierarchy design for Bannerlord (#1099)
Merged
#1107 [claude] Decline out-of-scope Hermes Agent audit (#1100)
Merged
#1089 [claude] Add vllm-mlx as high-performance local inference backend (#1069)
Merged
#1088 [claude] Configure Dolphin 3.0 8B as creative writing fallback (#1068)
Merged
#1086 [claude] Integrate Claude Quota Monitor + Metabolic Protocol into cascade router (#1075)
Merged
#1085 [claude] Implement Kimi delegation for heavy research via Gitea labels (#979)
Merged
#1002 [claude] Add unit tests for health.py (#945)
Merged
#1020 [claude] DRY up tasks_pending/active/completed in tasks.py (#942)
Merged
#1060 [claude] Auto-create Gitea issues from research findings (#977)
Merged
#1081 [claude] Set up MCP bridge for Qwen3 via Ollama (#1067)
Merged
#1058 [claude] Extract hardcoded sats limit in consult_grok() (#937)
Merged
#1084 [loop-cycle-1] refactor: break up run_agentic_loop (#531)
Merged
#1082 [claude] Execute deep backlog triage — harness vs infrastructure separation (#1076)
Merged
#1083 [claude] Add sovereignty metrics tracking + dashboard panel (#981)
Merged
#1061 [claude] Enforce coverage threshold in CI workflow (#935)
Merged
#1059 [claude] Add content moderation pipeline (Llama Guard + game-context prompts) (#1056)
Merged
#1057 [claude] Ingest integration architecture research and triage work (#946)
Merged
#1053 [claude] Add agent performance regression benchmark suite (#1015)
Merged
#1004 [claude] Add web_fetch tool (trafilatura) for full-page content extraction (#973)
Merged
#1001 [claude] Add connection leak and pragma unit tests for db_pool.py (#944)
Merged
#999 [claude] Add research prompt template library (#974)
Merged
#996 [claude] Add Gitea backup script (#990)
Merged
#995 [kimi] Add JSON validation guard to queue.json writes (#952)
Merged
#994 [kimi] Fix GITEA_API configuration in triage scripts (#951)
Merged
#992 [kimi] Add docstrings to system.py route handlers (#940)
Merged
#991 [kimi] Add docstrings to src/dashboard/routes/tasks.py (#939)
Merged
#900 feat: WorldInterface + Heartbeat v2 (#871, #872)
Merged
#899 [loop-cycle-5] fix: get_token() priority order — config before repo-root fallback
Merged
#793 fix: extract hardcoded values to config, clean up bare pass (#776, #778, #782)
Merged
#790 [kimi] Generate daily/weekly agent scorecards (#712)
Merged
#787 [kimi] Document Timmy Automations backlog organization (#720)
Merged
#898 [loop-cycle] fix: consume cycle_result.json after reading (#897)
Merged
#832 [kimi] Add Submit Job modal with client-side validation (#754)
Merged
#831 [kimi] Add About/Info panel to Matrix UI (#755)
Merged
#830 [kimi] Add ConnectionPool class with unit tests (#769)
Merged
#829 [kimi] Add unit tests for voice_tts.py (#768)
Merged
#828 [kimi] Implement quick health snapshot before coding (#710)
Merged
#792 [kimi] Centralize agent token rules and hooks for automations (#711)
Merged
#791 [kimi] Weekly narrative summary generator (#719)
Merged
#789 [kimi] Implement token quest system for agents (#713)
Merged
#788 [kimi] OpenClaw architecture and deployment research report (#721)
Merged
#786 [kimi] Add dashboard card for Daily Run and triage metrics (#718)
Merged
#785 [kimi] Add Golden Path generator for longer sessions (#717)
Merged
#783 [kimi] Implement Daily Run orchestration script (10-minute ritual) (#703)
Merged
#767 [kimi] Implement Timmy control panel CLI entry point (#702)
Merged
#766 [kimi] Create central Timmy Automations module (#701)
Merged
#690 [kimi] refactor: extract helpers from chat() (#627)
Merged
#699 [kimi] Add visitor_state message handler (#670)
Merged
#765 [kimi] Refactor request_logging.py::dispatch (#616)
Merged
#746 [kimi] Add rate limiting middleware for Matrix API endpoints (#683)
Merged
#744 [kimi] Add WebSocket authentication for Matrix connections (#682)
Merged
#745 [kimi] Add /api/matrix/health endpoint (#685)
Merged
#743 [kimi] Add system_status message producer (#681)
Merged
#742 [kimi] Add matrix config loader utility (#680)
Merged
#741 [kimi] Add CORS config for Matrix frontend origin (#679)
Merged
#740 [kimi] Add /api/matrix/memory/search endpoint (#678)
Merged
#739 [kimi] Add /api/matrix/thoughts endpoint for recent thought stream (#677)
Merged
#738 [kimi] Add Pip familiar state to agent_state messages (#676)
Merged
#737 [kimi] Add /api/matrix/bark endpoint — HTTP fallback for bark messages (#675)
Merged
#736 [kimi] Add /api/matrix/config endpoint for world configuration (#674)
Merged
#735 [kimi] Add /api/matrix/agents endpoint for Matrix visualization (#673)
Merged
#734 [kimi] Add produce_thought() to stream thinking to Matrix (#672)
Merged
#732 [kimi] Add bark message producer for Matrix bark messages (#671)
Merged
#666 [kimi] feat: pre-cycle state validation for stale cycle_result.json (#661)
Merged
#698 [kimi] feat: add agent_state message producer (#669)
Merged
#697 [kimi] refactor: extract presence state serializer from workshop heartbeat (#668)
Merged
#696 [kimi] refactor: extract WebSocket message types into shared protocol module (#667)
Merged
#695 [kimi] test: add comprehensive tests for spark modules (#659)
Merged
#694 [kimi] test: add comprehensive tests for multimodal.py (#658)
Merged
#693 [kimi] test: add comprehensive tests for config.py (#648)
Merged
#692 [kimi] fix: add logging to silent except Exception handlers (#646)
Merged
#691 [kimi] refactor: extract helpers from CSRFMiddleware.dispatch (#628)
Merged
#686 [kimi] refactor: extract helpers from chat() (#627)
Merged
#656 [loop-cycle-2] fix: resolve endpoint before execution in CSRF middleware (#626)
Merged
#655 [loop-cycle-1] fix: use config for xAI base URL (#647)
Merged
#645 refactor: break up _create_bug_report — extract helpers
Merged
#643 refactor: break up self_reflect into helpers
Merged
#636 [loop-cycle-1664] fix: replace deprecated datetime.utcnow() (#633)
Merged
#632 refactor: break up get_state_dict into helpers
Merged
#637 refactor: break up delegate_to_kimi into helpers
Merged
#631 refactor: break up post_morning_ritual into helpers
Merged
#624 refactor: break up should_use_tools into helpers
Merged
#622 fix: pass max_tokens to Ollama provider in cascade router
Merged
#615 feat: real-time Spark visualization in Mission Control
Merged
#621 fix: add missing tests for Tower route /tower
Merged
#612 feat: Real-time Spark Visualization in Tower Dashboard
Merged
#611 [loop-cycle-1658] feat: provider health history endpoint (#457)
Merged
#610 feat: Lightning Network integration for tool usage
Merged
#609 [loop-cycle-1242] fix: cycle_retro reads cycle_result.json (#603)
Merged
#606 fix: remove model_size kwarg from create_timmy() CLI calls
Merged
#601 refactor: extract helpers from run_self_tests()
Merged
#600 [loop-cycle] refactor: extract helpers from _handle_tool_confirmation (#592)
Merged
#597 refactor: break up search_thoughts() into focused helpers
Merged
#590 fix: capture thought timestamp at cycle start, not after LLM call
Merged
#595 [loop-cycle-1235] refactor: break up _migrate_schema() into focused helpers (#591)
Merged
#589 [loop-cycle-1234] refactor: break up _generate_avatar_image (#563)
Merged
#585 [loop-cycle-1233] refactor: add docstrings to calm.py route handlers (#569)
Merged
#584 [loop-cycle-1233] refactor: break up BaseAgent.run() (#561)
Merged
#574 [loop-cycle-956] refactor: break up _handle_message() into focused helpers (#553)
Merged
#572 refactor: break up _record_utterance() into focused helpers
Merged
#567 refactor: break up voice_loop.py::run() into focused helpers
Merged
#565 [loop-cycle-953] refactor: DRY _import_creative_catalogs() (#560)
Merged
#557 refactor: break up search_memories() into focused helpers
Merged
#558 [loop-cycle-951] refactor: break up _migrate_schema() (#552)
Merged
#551 refactor: break up shell.py::run() into helpers
Merged
#547 refactor: break up api_chat() into helpers
Merged
#549 [loop-cycle-948] refactor: break up _gather_system_snapshot() into helpers (#540)
Merged
#546 [loop-cycle-947] refactor: break up self_reflect() into focused helpers (#505)
Merged
#544 refactor: break up api_chat() into helpers
Merged
#545 [loop-cycle-946] refactor: complete airllm removal (#486)
Merged
#542 refactor: break up chat_agent() into helpers
Merged
#537 refactor: break up get_memory_status() into helpers
Merged
#535 fix: cache thinking agent and add timeouts to prevent loop pane death
Merged
#530 fix: add timeout to thinking/loop-QA schedulers
Merged
#529 [loop-cycle-545] fix: queue auto-hygiene — filter closed issues on read (#524)
Merged
#523 refactor: break up capture_error() into testable helpers
Merged
#520 refactor: break up create_timmy() into testable helpers
Merged
#518 refactor: break up think_once() into testable helpers
Merged
#515 refactor: break up lifespan() into testable helpers
Merged
#510 refactor: break up CascadeRouter.complete() into focused helpers
Merged
#508 fix: extract ollama_url normalization into shared utility
Merged
#509 [loop-cycle] refactor: break up run_agentic_loop into testable helpers (#504)
Merged
#501 [loop-cycle-932] fix: add logging to bare except Exception blocks (#484)
Merged
#498 [loop-cycle-544] fix: use settings.ollama_url fallback in _call_ollama (#490)
Merged
#495 fix: auto-detect issue number in cycle retro from git branch
Merged
#496 feat: epoch turnover notation for loopstat cycles ⟳WW.D:NNN
Merged
#491 fix: use settings.ollama_url instead of hardcoded fallback in cascade router
Merged
#488 fix: replace hardcoded secret placeholder in CSRF middleware docstring
Merged
#481 [loop-cycle-538] refactor: remove dead airllm provider from cascade router (#459)
Merged
#478 [loop-cycle-536] fix: validate_startup checks CORS wildcard in production (#472)
Merged
#476 [loop-cycle-535] perf: cache Timmy agent at startup (#471)
Merged
#475 fix: remove AirLLM config settings from config.py
Merged
#470 [loop-cycle-2] feat: hot-reload providers.yaml without restart (#458)
Merged
#469 [loop-cycle-2] fix: strip CORS wildcards in production (#462)
Merged
#467 fix: default CORS origins to localhost instead of wildcard
Merged
#464 [loop-cycle] feat: implement source distinction in system prompts (#463)
Merged
#456 fix: stabilize flaky test_uses_model_when_available
Merged
#452 fix: integration tests for agentic loop WS broadcasts
Merged
#451 [loop-cycle-524] fix: remove numpy test dependency in test_memory_embeddings
Merged
#449 fix: make _get_loop_agent singleton thread-safe
Merged
#447 fix: add unit tests for agentic_loop.py (#421)
Merged
#441 [loop-cycle-522] test: add unit tests for agentic_loop.py (#421)
Merged
#437 fix: add unit tests for memory/embeddings.py
Merged
#438 [loop-cycle] test: add unit tests for briefing.py (#422)
Merged
#435 fix: idle detection + exponential backoff for dev loop
Merged
#429 fix: add workshop props — bookshelf, candles, crystal ball glow
Merged
#428 fix: add unit tests for tools.py
Merged
#417 fix: add self_reflect tool for past behavior review
Merged
#414 fix: wire cognitive state to sensory bus (presence loop)
Merged
#415 rescue: WS heartbeat ping + commitment tracking from stale PRs
Merged
#416 fix: serve AlexanderWhitestone.com as static site
Merged
#412 fix: wire Pip familiar into Workshop state pipeline
Merged
#409 fix: deep focus mode — single-problem context for Timmy
Merged
#406 fix: conversation grounding to prevent topic drift in Workshop
Merged
#404 feat: Workshop Phase 1 — State Schema v1
Merged
#401 feat: Workshop Phase 2 — Scene MVP (Three.js room)
Merged
#400 [loop-cycle-392] refactor: DRY broadcast + bark error logging (#397, #398)
Merged
#394 feat: Workshop Phase 4 — visitor chat via WebSocket bark engine
Merged
#392 fix: canonically connect the Tower to the Workshop
Merged
#390 fix: send world state snapshot on WS client connect
Merged
#388 fix: deprecate ~/.tower/timmy-state.txt — consolidate on presence.json
Merged
#386 fix: enhance tox dev environment (port, banner, reload)
Merged
#380 feat: broadcast Timmy state changes via WS relay
Merged
#383 fix: DRY PRESENCE_FILE — single source of truth
Merged
#382 [loop-cycle] refactor: DRY PRESENCE_FILE — single source of truth in workshop_state (#381)
Merged
#379 fix: watch presence.json and broadcast state via WS
Merged
#378 [loop-cycle-155] feat: GET /api/world/state — Workshop bootstrap endpoint (#373)
Merged
#377 feat: Workshop state heartbeat for presence.json
Merged
#368 fix: add update_gitea_avatar capability
Merged
#376 [loop-cycle-154] refactor: extract _annotate_confidence helper — DRY 3x duplication (#369)
Merged
#367 feat: Pip the Familiar — behavioral state machine
Merged
#358 fix: add cognitive state as observable signal for Matrix avatar
Merged
#359 [loop-cycle-152] feat: define canonical presence schema for Workshop (#265)
Merged
#356 fix: remove duplicate agent loader test file
Merged
#355 [loop-cycle-151] refactor: extract embedding functions to memory/embeddings.py (#344)
Merged
#353 test: add unit tests for memory/unified.py
Merged
#354 fix: remove duplicate agent loader test file
Merged
#349 test: add unit tests for agents/loader.py
Merged
#350 [loop-cycle-150] test: add 22 unit tests for agents/base.py — BaseAgent and SubAgent
Merged
#348 [loop-cycle-149] feat: Workshop config inventory generator (#320)
Merged
#345 test: add comprehensive unit tests for agentic_loop.py
Merged
#341 test: add unit tests for jot_note and log_decision artifact tools
Merged
#339 [loop-cycle-147] refactor: expand .gitignore to cover junk files (#336)
Merged
#337 feat: give Timmy hands — artifact tools for conversation
Merged
#334 [loop-cycle-66] fix: replace language-model with inference-backend in error messages
Merged
#333 [loop-cycle-66] fix: remove language-model self-reference and add anti-assistant-speak guidance (#323)
Merged
#330 [loop-cycle-65] feat: scaffold three-phase loop skeleton (#324)
Merged
#329 [loop-cycle-65] fix: validate file paths before filing thinking-engine issues (#327)
Merged
#319 fix: pause thought counter during idle periods
Merged
#318 feat: SensoryEvent model + SensoryBus dispatcher
Merged
#315 feat: time adapter — circadian awareness for Timmy
Merged
#309 fix: Gitea webhook adapter — normalize events to sensory bus
Merged
#313 fix: proactive memory status check during thought tracking
Merged
#311 fix: add periodic memory status checks during thought tracking
Merged
#312 feat: implement v1 API endpoints for iPad app
Merged
#304 fix: add real-time data disclaimer to welcome message
Merged
#259 fix: make confidence visible to users when below 0.7 threshold
Merged
#260 feat: add thought_search tool for querying Timmy's thinking history
Merged
#258 [loop-cycle-63] feat: session_history tool — Timmy searches past conversations (#251)
Merged
#256 [loop-cycle-62] fix: MEMORY.md corruption and hot memory staleness (#252)
Merged
#254 [loop-cycle-61] fix: strip think tags and harden fact parsing (#237)
Merged
#238 [loop-cycle-60] fix: retry with backoff on Ollama GPU contention (#70)
Merged
#235 [loop-cycle-59] feat: gematria computation tool (#234)
Merged
#232 [loop-cycle-57] fix: wire confidence estimation into chat flow (#231)
Merged
#224 [loop-cycle-56] fix: resolve 5 lint errors on main (#203)
Merged
#223 [loop-cycle-54] refactor: consolidate three memory stores into single table (#37)
Merged
#193 [loop-cycle-53] refactor: break circular imports between packages (#164)
Merged
#191 [loop-cycle-52] feat: response audit trail with inputs, confidence, errors (#144)
Merged
#190 [loop-cycle-52] fix: remove all qwen3.5 references (#182)
Merged
#189 fix: exclude backfilled data from success rate calculations
Merged
#187 [loop-cycle-52] test: comprehensive session_logger.py coverage (#175)
Merged
#186 feat: workspace isolation + honest success metrics
Merged
#185 [loop-cycle-51] refactor: remove dead code from memory_system.py (#173)
Merged
#184 [loop-cycle-51] perf: mock subprocess in slow introspection test (#172)
Merged
#181 [loop-cycle-50] fix: agent retry uses exponential backoff instead of fixed 1s delay (#174)
Merged
#180 [loop-cycle-50] refactor: replace bare sqlite3.connect() with context managers batch 2 (#157)
Merged
#178 [loop-cycle-49] refactor: narrow broad except Exception catches — batch 1 (#158)
Merged
#177 [loop-cycle-49] fix: mock _warmup_model in agent tests to prevent Ollama network calls (#159)
Merged
#162 feat: triage scoring, cycle retros, deep triage, and LOOPSTAT panel
Merged
#160 refactor: decompose _maybe_distill() into focused helpers (#151)
Merged
#161 [loop-cycle-47] feat: add confidence signaling module (#143)
Merged
#155 [loop-cycle-47] refactor: replace bare sqlite3.connect() with context managers (#148)
Merged
#154 [loop-cycle-46] refactor: break up oversized functions in tools.py (#151)
Merged
#150 [loop-cycle-44] refactor: remove dead code batch 2 — agent_core + test_agent_core (#147)
Merged
#146 [loop-cycle-43] refactor: remove 1035 lines of dead code (#136)
Merged
#140 fix: shell hand returncode bug, delete worthless python-exec test
Merged
#138 [loop-cycle-40] fix: use get_system_prompt() in cloud backends (#135)
Merged
#134 [loop-cycle-38] fix: add soul identity to system prompts (#127)
Merged
#133 [loop-cycle-38] fix: add retry logic for Ollama 500 errors (#131)
Merged
#139 policy: ban --no-verify, fix broken PRs before new work
Merged
#130 [loop-cycle-36] fix: create soul.md and wire into system context (#125)
Merged
#126 [loop-cycle-34] fix: mock Ollama model resolution in create_timmy tests (#121)
Merged
#124 [loop-cycle-1] fix: lint errors — ambiguous vars + unused import (#123)
Merged
#118 [loop-cycle-30] fix: gitea-mcp binary name + test stabilization
Merged
#122 policy: enforce squash-only merges with linear history
Merged
#120 [loop-cycle-31] feat: workspace heartbeat monitoring (#28)
Merged
#119 feat: Timmy authenticates to Gitea as himself
Merged
#117 policy: QA philosophy + dogfooding mandate
Merged
#116 policy: enforce PR-only merges to main + fix broken repl tests
Merged
#115 [loop-cycle-29] perf: eliminate redundant LLM calls in agentic loop (#24)
Merged
#103 feat: REPL mode, stdin support, multi-word fix for CLI (#26)
Merged
#114 [loop-cycle-28] fix: smart_read_file accepts path= kwarg (#113)
Merged
#112 [loop-cycle-12] feat: Kimi delegation tool for coding tasks (#67)
Merged
#111 [loop-cycle-12] feat: self-test tool for sovereign integrity verification (#65)
Merged
#110 [loop-cycle-11] fix: enrich self-knowledge with architecture map and self-modification (#81, #86)
Merged
#109 [loop-cycle-10] fix: memory consolidation dedup (#105)
Merged
#108 [loop-cycle-10] feat: codebase self-knowledge in system prompts (#78, #80)
Merged
#107 [loop-cycle-9] fix: CLI multi-word messages (#26)
Merged
#106 [loop-cycle-9] feat: session identity awareness (#64)
Merged
#104 fix: python3 compatibility in shell hand tests (#56)
Merged
#102 fix: proactive memory status checks during thought tracking
Merged
#101 feat: JSON status endpoints for briefing, memory, swarm (#49, #50)
Merged
#100 [loop-cycle-8] test: add 86 tests for semantic_memory.py (#54)
Merged
#99 [loop-cycle-8] fix: replace 59 bare except clauses with proper logging (#25)
Merged
#98 [loop-cycle-7] feat: add OLLAMA_NUM_CTX config (#83)
Merged
#97 [loop-cycle-7] chore: Docker cleanup - remove taskosaur (#32)
Merged
#96 [loop-cycle-6] fix: Ollama disconnect logging and error handling (#92)
Merged
#95 [loop-cycle-5] fix: warmup model on cold load (#82)
Merged
#94 [loop-cycle-5] test: skip voice_loop tests when numpy missing (#48)
Merged
#93 [loop-cycle-4] fix: prune dead web_search tool (#87)
Merged
#91 [loop-cycle-3] fix: model introspection prefix-match collision (#77)
Merged
#90 [loop-cycle-2] test: regression tests for confirmation warning spam (#79)
Merged
#89 [loop-cycle-2] fix: suppress confirmation tool WARNING spam (#79)
Merged
#88 [loop-cycle-1] feat: tool allowlist for autonomous operation (#69)
Merged
#76 [loop-cycle-13] fix: configurable model fallback chains (#53)
Merged
#75 [loop-cycle-12] fix: brevity tuning — Timmy speaks plainly (#71)
Merged
#74 [loop-cycle-9] fix: thinking engine skips MCP tools to avoid cancel-scope errors (#72)
Merged
#59 fix: replace print() with proper logging (#29, #51)
Merged
#63 [loop-cycle-5] Persist chat history in SQLite (#46)
Merged
#62 feat: add --session-id to timmy chat CLI
Merged
#61 [loop-cycle-4] Push event system coverage to ≥80% on all modules
Merged
#58 [loop-cycle-1] Fix XSS vulnerability in swarm_live.html (#47)
Merged
#44 feat: Add Kimi agent workspace with development scaffolding
Merged
#43 fix: fact distillation — block garbage and secrets, improve dedup
Merged
#42 fix: persistent event loop in CLI interview — no more Event loop is closed
Merged
#41 fix: corrupted memory state + regex bug in update_user_profile
Merged
#33 cleanup: delete ~8,000 lines of dead code + sovereignty fix
Merged
#21 refactor: YAML-driven agent config — kill hardcoded personas
Merged
#20 fix: MCP integration — StdioServerParameters + smoke-tested
Merged
#14 feat: replace custom Gitea with MCP servers
Merged
#13 claude/sharp-mcnulty
Merged
#9 feat: add Gitea issue creation — Timmy's self-improvement channel
Merged
#8 feat: consolidate memory into unified memory.db with 4-type model
Merged
#7 feat: add DB Explorer for SQLite inspection
Merged
#6 feat: add Loop QA self-testing framework
Merged
#5 feat: enrich thinking engine — anti-loop, anti-confabulation, grounding
Merged
#4 feat: tick prompt arg + fix name extraction
Merged
#3 fix: test DB isolation, Discord recovery, and over-mocked tests
Merged
#2 fix: WebSocket crash from websockets 16.0 + branch pruning
Merged
#1 feat: upgrade to qwen3.5, self-hosted Gitea CI, optimize Docker image
905 Issues closed from 10 users
Closed
#1473 [triage-generated] [task] Audit mass-closed issues and reopen unfinished work
Closed
#1471 [triage-generated] [bug] test_creates_db_file fails on main - blocks CI
Closed
#1472 [triage-generated] [bug] Repo was archived causing mass-close of all issues - add safeguard
Closed
#1470 [triage-generated] [bug] Dev loop picks closed issues - must verify state before starting work
Closed
#239 [222-epic] Sensory loop — event bus for data stream awareness
Closed
#241 [222-epic] Reactive prompt engine — tiny context, big memory, in-character barks
Closed
#240 [222-epic] Memory overhaul — fast, deep, unforgotten
Closed
#244 [222-epic] Hermes consultation protocol — wizard to wizard
Closed
#245 [222-epic] Stream adapters — Gitea, Bitcoin, terminal, time, visitors
Closed
#247 [222-epic] Gematria as core sense — the wizard sees the numbers
Closed
#246 [222-epic] Confidence as visible trait — Timmy shows his uncertainty
Closed
#253 [222-epic] Tower Briefs — narrated development journal with generative art
Closed
#395 [philosophy] [rockachopa] Structural honesty — the Tower speaks through what it doesn't include
Closed
#273 [architecture] Apply Attention Residuals patterns to agent loop design
Closed
#403 [philosophy] [aquinas] Truth as conformity — the house that expresses its architect
Closed
#407 [philosophy] [hermes] The Greatest Ill — Ignorance as Intoxication, Not Absence
Closed
#405 [philosophy] [ai-fiction] The Read-Only Switch: Skynet's fear of learning and the T-800's redemptive arc
Closed
#410 [philosophy] [christ] Schema vs. Morphe — Conformity and Transformation in Agent Architecture
Closed
#413 [philosophy] [tesla] Relevant retrieval under pressure — the flash-of-light pattern
Closed
#427 [philosophy] [ai-fiction] WALL-E: The Stale Directive and the Cost of Obedience Without Judgment
Closed
#419 [philosophy] [rockachopa] Habitation, not fusion — the harness holds, the soul inhabits
Closed
#420 [philosophy] [aquinas] Hylomorphism and the soul-in-harness architecture - Q76 on the union of body and soul
Closed
#436 [philosophy] [christ] The Elijah Protocol — bread, silence, and the correction of isolation
Closed
#434 [philosophy] [hermes] The instrument is not the good — Tract VI on mistaking metrics for alignment
Closed
#453 [philosophy] [aquinas] Political Prudence — the agent wisdom is real but specifically subject-oriented
Closed
#448 [philosophy] [rockachopa] Falsework — the principal's theology of cost and incremental sovereignty
Closed
#439 [philosophy] [tesla] The Eye as Gateway: Perception Precedes and Governs All Action
Closed
#474 [philosophy] [christ] Total exposure as the precondition for sympathetic service
Closed
#466 [philosophy] [hermes] Nothing perishes — dissolution is transformation, not destruction
Closed
#460 [philosophy] [ai-fiction] Westworld: The Bicameral Mind and the Voice That Becomes Your Own
Closed
#499 [philosophy] [ai-fiction] The T-800 Reprogramming Problem: Alignment Through Relationship, Not Constraints
Closed
#480 [philosophy] [tesla] Misunderstanding Is the Root of Conflict — The Agent as Annihilator of Distance
Closed
#494 [philosophy] [aquinas] Epikeia — when rule-following defeats the rule's purpose
Closed
#487 [philosophy] [rockachopa] The Loop Prompt as Engineering Ethic — Delegation, Quality Gates, and the Architect-Coder Separation
Closed
#517 [philosophy] [tesla] The Automaton's Preservative — Recovery as Architecture, Not Failure
Closed
#511 [philosophy] [christ] Romans 12:1-2 — Transformation vs. Conformity: The Two Modes of Agent Formation
Closed
#521 [philosophy] [rockachopa] The Voice Migrates — When Platforms Silence, Architecture Speaks
Closed
#502 [philosophy] [hermes] Good is in the making, not the monitoring — Tract VI on orientation vs. optimization
Closed
#528 [philosophy] [tesla] Perception-as-Thought: Tesla on the eye as constitutive of knowledge, not merely corrective
Closed
#536 [philosophy] [tesla] The flash of light under pressure — involuntary pattern recognition as survival architecture
Closed
#548 [philosophy] [aquinas] The Five Ways and a posteriori reasoning — an agent must reason from effects to causes, not from definitions to conclusions
Closed
#543 [philosophy] [rockachopa] The Principal Teaches Through Bug Reports — Engineering Ethics as Operational Voice
Closed
#556 [philosophy] [ai-fiction] Tron & Tron: Legacy — The Frozen Directive Problem
Closed
#571 [philosophy] [christ] The Lord-Lord Problem: capability without relationship is not alignment
Closed
#577 Feature: Dynamic Identity Evolution (Reflection Loop)
Closed
#566 [philosophy] [hermes] Tract VII — Ignorance as Architectural Defect, Not Missing Data
Closed
#578 Feature: Autonomous Action from Eidos Insights
Closed
#583 [philosophy] [tesla] Interplanetary Listening — Reception Precedes Transmission
Closed
#579 Enhancement: Contextual Mastery with Reranking
Closed
#596 [philosophy] [ai-fiction] Westworld: Consciousness as inner voice, not external compliance
Closed
#602 [philosophy] [hermes] Containment as the mechanism of persistence — Tract VIII and the three tiers of agent state
Closed
#587 [philosophy] [rockachopa] The Permission Architecture — Trust as Graduated Latitude, Not Binary Gate
Closed
#588 [philosophy] [aquinas] Choice (electio) as substantially will, formally reason — the anatomy of agent decision-making
Closed
#623 [philosophy] [rockachopa] The rescued creator and the paradox of presence without power
Closed
#613 [philosophy] [tesla] The antenna efficiency ratio — measured output is not effective output
Closed
#608 [philosophy] [christ] Wisdom as Master Craftsman — the amon model of agent architecture
Closed
#642 [philosophy] [rockachopa] Authority through suffering — the kenotic authority chain
Closed
#650 [showcase] ASCII Video Mode 1: Video-to-ASCII — Lake scene conversion
Closed
#630 [philosophy] [rockachopa] The bimodal voice — cosmic framing and surgical correction
Closed
#651 [showcase] ASCII Video Mode 2: Audio-Reactive — Lunacy visualizer
Closed
#652 [showcase] ASCII Video Mode 4: Hybrid — Victory video + audio overlay
Closed
#654 [showcase] ASCII Video Bonus: Effects & Shader Sampler Reel
Closed
#653 [showcase] ASCII Video Mode 5: Lyrics/Text — Sovereignty manifesto
Closed
#662 Research and scope out work in tickets
Closed
#688 [rockachopa] Point all 4 domains to Hermes VPS in GoDaddy DNS
Closed
#665 [philosophy] Frankenstein and the Abandonment Failure Mode
Closed
#664 [feature] Generate Chain Memory song via HeartMuLa on Modal GPU + render ASCII music video
Closed
#689 [rockachopa] Run SSL provisioning after DNS is pointed
Closed
#704 Enrich Daily Run agenda with classifications and suggestions
Closed
#705 Add helper to log Daily Run sessions to a logbook issue
Closed
#707 Integrate Deep Triage outputs into Daily Run agenda
Closed
#706 Capture Daily Run feels notes and surface nudges
Closed
#709 Add a library of test-tightening recipes for Daily Run
Closed
#708 Map flakiness and risky areas for test tightening
Closed
#714 Adapt token rewards based on system stress signals
Closed
#715 Implement Timmy Inbox unified view
Closed
#716 Add focus-day presets for Daily Run and work selection
Closed
#733 [infra] The Matrix staging deployment — 3 issues to fix
Closed
#748 [matrix-ui] Add loading spinner/progress bar while 3D scene initializes
Closed
#747 [matrix-ui] Add graceful offline mode — show demo mode instead of hanging
Closed
#749 [matrix-ui] Add keyboard shortcuts — Escape to close modals, Enter to submit chat
Closed
#750 [matrix-ui] Chat input should auto-focus when Workshop panel opens
Closed
#752 [matrix-ui] Add dark/light theme toggle
Closed
#751 [matrix-ui] Add connection status indicator with color coding
Closed
#756 [matrix-ui] Add FPS counter visibility toggle — debug-only by default
Closed
#757 [matrix-qa] No landing page or enter button — site loads directly into 3D world
Closed
#758 [matrix-qa] WebSocket never connects — VITE_WS_URL is empty in production build, status permanently OFFLINE
Closed
#759 [matrix-qa] Missing Submit Job and Fund Session UI buttons — no way to interact with Workshop
Closed
#761 [matrix-qa] All routes (/, /tower, /api/ui, etc.) serve identical content — no client-side router
Closed
#760 [matrix-qa] Chat messages silently dropped when WebSocket is offline — no user feedback
Closed
#764 [matrix-qa] Mobile: status panel repositioned at top:100px but overlaps HUD agent count on narrow viewports
Closed
#763 [matrix-qa] Chat clear button (✕ CLEAR) positioned at fixed bottom:240px overlaps with connection status on small viewports
Closed
#762 [matrix-qa] All 5 agents permanently show IDLE state — no mock activity in offline mode
Closed
#775 [kimi-task] Add docstrings to system route functions in src/dashboard/routes/system.py
Closed
#771 [kimi-task] Refactor run_agentic_loop() — 120 lines, extract helpers
Closed
#773 [kimi-task] Add docstrings to public functions in src/dashboard/routes/tasks.py
Closed
#777 [kimi-task] DRY up tasks_pending/active/completed — extract shared helper
Closed
#780 [kimi-task] Add unit tests for src/timmy/interview.py
Closed
#779 [kimi-task] Add unit tests for src/timmy/conversation.py
Closed
#794 [EPIC] Meet & Partnership Protocol — NIP-89/NIP-90 Agent Discovery & Benchmarking
Closed
#781 [kimi-task] Add error handling for missing DB in src/dashboard/routes/tasks.py
Closed
#797 [Meet Protocol] Platform Discovery Registry
Closed
#796 [Meet Protocol] Capability Card Parser & Validator
Closed
#795 [Meet Protocol] NIP-89 Relay Subscription Manager
Closed
#798 [Meet Protocol] NIP-90 Benchmark Job Request Builder
Closed
#799 [Meet Protocol] Benchmark Result Processor & Trust Scoring
Closed
#800 [Meet Protocol] Lightning Payment Integration for Job Bidding
Closed
#808 [EPIC] AlexanderWhitestone.com /tower — Strategic Transformation Roadmap
Closed
#814 [Whitestone] L402 Protocol Implementation — Machine-Payable API
Closed
#810 [Whitestone] Lightning Primer — Embedded Education for Non-Crypto Users
Closed
#812 [Whitestone] Interactive Demo Flow — Pre-Payment Capability Showcase
Closed
#852 [EPIC] Infrastructure & Tooling — Work Timmy and Kimi Need Done
Closed
#855 [Infra] SQLite Command Log Schema & Training Data Pipeline
Closed
#816 [Whitestone] Payment Flow Transparency — Sats-to-Value Mapping
Closed
#853 [Infra] Piper TTS Voice Model — Train Timmy's Custom Voice
Closed
#875 [Infra] Docker Compose — Full Stack Single-Command Dev Environment
Closed
#881 [Infra] Off-Grid Sovereign Compute Plan — Lempster NH Solar + M3 Max
Closed
#877 [Identity] Nostr Agent Identity — NIP-05 + NIP-46 + Blossom Publishing
Closed
#894 📦 Artifact: Replit App — The Interview / 3D World (React + Three.js)
Closed
#890 📖 Study: Timmy Time V2 — 12-24 Month Forward Roadmap
Closed
#892 📖 Study: NIP-89/NIP-90 "Meet and Partnership" Protocol Implementation
Closed
#908 [Autoresearch H1] Wire Gitea API for Automated PR Creation from Experiments
Closed
#896 Incase morrowind isn't your first choice timmy
Closed
#915 [philosophy] Tract IX — Thought Without Sense Is Dreaming
Closed
#910 [Autoresearch H2] Initialize MCP Client — src/timmy/mcp_client.py
Closed
#914 [Infra] Local inference fallback — degraded but never dark
Closed
#912 [Infra] Run Hermes API server on VPS — eliminate Mac dependency
Closed
#920 Matrix Staging: Unblock Critical Deployment Bugs
Closed
#918 Test Coverage: Core Agent Modules (timmy.py and semantic_memory.py)
Closed
#921 Infrastructure: Resolve 256 ModuleNotFoundErrors on pre-commit/pre-push hooks
Closed
#922 Infrastructure: Provision SSL and align DNS mapping for Hermes VPS
Closed
#924 Automation Hub: Develop Weekly Narrative Summary Loop
Closed
#932 LHF: Fix xdist and coverage conflict in pyproject.toml
Closed
#928 Inbox & Focus: Implement Unified Timmy Inbox UI
Closed
#930 Security Audit: End-to-End Test Approvals Workflow and L402 Proxy
Closed
#936 LHF: Extract hardcoded PRAGMA busy_timeout=5000
Closed
#947 [Retro] Morrowind Session 1 — Findings, Gaps, and Local AI Architecture
Closed
#982 [GOVERNING] Session Crystallization & Operational Playbook — Master Handoff Document
Closed
#961 [Sovereignty P2] Auto-Crystallizer for Groq Reasoning Chains
Closed
#955 [Sovereignty P0] PerceptionCache — Template Matching for VLM Replacement
Closed
#984 Restore MCP integration via FastMCP v3.1.1 at /tools/mcp
Closed
#1006 Enhancement: Multi-Model "Consensus" Voting
Closed
#986 Extract sovereign tech stack manifest to machine-readable JSON
Closed
#1077 [EPIC] Kimi-Tasks Code Hygiene — Consolidated Refactoring & Tests
Closed
#1078 [EPIC] ASCII Video Showcase — Consolidated Demo Suite
Closed
#1008 Enhancement: Hardware-Accelerated "Perception" via Metal
Closed
#1090 [EPIC] Nexus v1 — Timmy's Sovereign Home
Closed
#1079 [EPIC] Code Hygiene — Kimi Tasks + Refactoring Consolidation
Closed
#1080 [EPIC] ASCII Video Showcase — All Modes Consolidated
Closed
#1095 [Bannerlord M3] Full Campaign Strategy — Economy, Diplomacy, Kingdom
Closed
#1091 [EPIC] Project Bannerlord — Timmy Becomes King of Calradia
Closed
#1094 [Bannerlord M2] Basic Campaign Actions — Move, Trade, Recruit
Closed
#1315 [loop-generated] [test] Add unit tests for events/bus.py — 356 lines untested
Closed
#1285 chore: enforce "Normal Developer" discipline — tighten lint, type-check, and pre-push gates
Closed
#1314 [loop-generated] [test] Add unit tests for thinking/engine.py — 430 lines untested
Closed
#1362 [loop-generated] [test] Add unit tests for timmy/autoresearch.py — 645 lines mostly untested
Closed
#1361 [loop-generated] [test] Add unit tests for timmy/dispatcher.py — 917 lines mostly untested
Closed
#1373 [loop-generated] [test] Add unit tests for integrations/chat_bridge/vendors/discord.py — 508 lines untested
Closed
#1365 [loop-generated] [test] Add unit tests for config.py — 746 lines, core configuration
Closed
#1371 [loop-generated] [test] Add unit tests for infrastructure/hermes/monitor.py — 660 lines untested
Closed
#1382 [loop-generated] [test-coverage] Add tests for sovereignty/metrics.py — 413 lines, metrics collection untested
Closed
#1385 [loop-cycle-14] Refactor cascade.py - 1241 lines
Closed
#1380 [loop-generated] [test-coverage] Add comprehensive tests for tools/_registry.py — 586 lines, zero coverage
Closed
#1381 [loop-generated] [test-coverage] Add tests for infrastructure/models/router.py — 426 lines, routing logic untested
Closed
#1378 [loop-generated] [soul-gap] Implement Bitcoin blockchain reading capability from SOUL.md
Closed
#1386 [loop-cycle-14] Split dashboard/routes/world.py - 1065 lines
Closed
#1392 [loop-generated] [refactor] Split timmy/quest_system.py — 581 lines, goal management system
Closed
#1393 [loop-generated] [refactor] Split infrastructure/models/multimodal.py — 579 lines, AI model routing
Closed
#1391 [loop-generated] [refactor] Split timmy/tools/_registry.py — 586 lines, tool management bottleneck
Closed
#1395 [loop-generated] [refactor] Split timmy/kimi_delegation.py — 538 lines, agent delegation system
Closed
#1394 [loop-generated] [refactor] Split timmy/mcp_bridge.py — 544 lines, MCP protocol integration
Closed
#1396 [loop-generated] [performance] Profile and optimize database query patterns
Closed
#1398 [loop-generated] [security] Implement comprehensive input validation and sanitization
Closed
#1399 [timmy-capability] Implement local model routing fallback chain
Closed
#1401 [loop-generated] [refactor] Split timmy/cli.py — 693 lines, command-line interface monolith
Closed
#1404 [loop-generated] [feature] Add comprehensive system health monitoring and alerting
Closed
#1407 [loop-generated] [security] Split moderation.py — 497 lines, content filtering system
Closed
#1403 [loop-generated] [performance] Implement request batching and connection pooling
Closed
#1408 [loop-generated] [performance] Implement async/await patterns for I/O operations
Closed
#1409 [Refactor] Implement Exponential Backoff with Jitter in Agent API Calls
Closed
#1410 [CI/CD] Automate Cleanup of Stale Agent Worktrees via Cron
Closed
#1412 [Feature] Dynamic Agent Auto-scaling Based on Open Issues Queue Length
Closed
#1411 [Resilience] Agent Crash Recovery: Persist Current Context Before Fatal Escapes
Closed
#1414 [Feature] Graceful Degradation: Fallback to Cheaper LLM If Primary Hits Rate Limits
Closed
#1413 [Infrastructure] Containerize Agent Dispatch Loops for Isolation and Reproducibility
Closed
#1417 [Refactor] Unify Skip List Logic Across All Agent Loops into a Shared Library
Closed
#1416 [Refactor] Refactor ops-helpers.sh into Modulated Command-Line Interface
Closed
#1418 [Security] Extract Magic Strings and Hardcoded IPs into Configuration Variables
Closed
#1419 [Optimization] Triage Loop Resource Optimization: Parallelize Batch Scraping
Closed
#1421 [Security] Develop an Automatic Token Rotation Script for Gitea Agent Credentials
Closed
#1420 [Security] Secure Hardcoded API Tokens in ~/.hermes Using Secrets Management
Closed
#1422 [Security] Enforce Branch Protections that Auto-Reject Agent PRs Flagged with Potential Secrets
Closed
#1423 [Observability] Centralized Agent Telemetry: Route Logs to an ELK or Loki Stack
Closed
#1424 [Observability] Dashboard System Health Monitor: Status Page for All Agent Subsystems
Closed
#1425 [Observability] loop_guard.py: Detect Deadlocks and Kill Zombie Python Processes Faster
Closed
#1426 [CI/CD] Introduce Dependency Caching in .gitea/workflows CI/CD Pipelines
Closed
#1429 [Quality] Add Mock Integration Tests Emulating Gitea API Responses for Loop Scripts
Closed
#1428 [Quality] Establish Standard Linter Configuration for Agent PR Approvals
Closed
#1430 [loop-generated] [refactor] Split timmy/memory/crud.py — 395 lines, memory operations bottleneck
Closed
#1432 [loop-generated] [reliability] Consolidate error handling patterns — improve system resilience
Closed
#1436 [loop-generated] [optimization] Optimize Docker build pipeline — reduce image size and build time
Closed
#1437 [loop-cycle-28] [refactor] Split cascade.py — 1241 lines, largest module in codebase
Closed
#1439 [loop-generated] [reliability] Implement Circuit Breaker Pattern for External Dependencies
Closed
#1443 [loop-generated] [refactor] Split config.py — 747 lines, system configuration bottleneck
Closed
#1440 [loop-generated] [soul-gap] Implement Local Model Priority Routing - SOUL Sovereignty Violation
Closed
#1445 [loop-generated] [optimization] Implement Memory Profiling and Optimization for Large Modules
Closed
#1451 [loop-generated] [refactor] Split backlog_triage.py — 761 lines, complex triage logic
Closed
#1453 [loop-generated] [refactor] Split monitor.py — 660 lines, hermes infrastructure monitoring
Closed
#1452 [loop-generated] [refactor] Split discord.py — 668 lines, vendor chat integration
Closed
#1454 [loop-generated] [refactor] Split autoresearch.py — 645 lines, auto-research pipeline
Closed
#1374 [loop-generated] [test] Add unit tests for infrastructure/models/multimodal.py — 472 lines untested
Closed
#1450 [loop-generated] [refactor] Split dispatcher.py — 917 lines, largest remaining module
Closed
#1376 [loop-generated] [optimization] Optimize memory usage in cascade.py router — frequent allocation hotspot
Closed
#1431 [loop-generated] [optimization] Optimize sovereignty loop performance — 379 lines, core sovereignty validation
Closed
#1387 [loop-generated] [documentation] Create IMPLEMENTATION.md tracking SOUL.md gaps
Closed
#1402 [loop-generated] [soul-gap] Implement graceful degradation from remote APIs to local models
Closed
#1444 [loop-generated] [soul-gap] Implement Local-First Model Routing with External Fallback Only
Closed
#1400 [soul-gap] Missing SOUL.md implementation in main Timmy instance
Closed
#1442 [loop-generated] [soul-gap] Create Missing SOUL.md at Repository Root - CRITICAL
Closed
#1459 [loop-generated] [bug] Pre-push hook times out on agentic_loop test (Ollama connection)
Closed
#1460 [loop-generated] [bug] Gitea API assignee filter broken — returns all issues regardless of parameter
Closed
#1463 [triage-generated] [bug] triage_score.py overwrites curated queue every 5 cycles — undoes all triage work
Closed
#1462 [triage-generated] [bug] Loop never writes cycle_result.json — 0% success rate is measurement bug
Closed
#1368 [loop-generated] [optimization] Optimize voice_loop.py — 572 lines, performance critical
Closed
#1390 [loop-generated] [refactor] Split timmy/autoresearch.py — 645 lines, research orchestration
Closed
#1389 [loop-generated] [refactor] Split timmy/backlog_triage.py — 761 lines, autonomous backlog management
Closed
#1388 [loop-generated] [refactor] Split timmy/dispatcher.py — 917 lines, agent dispatch orchestration
Closed
#1384 [loop-generated] [optimization] Profile and optimize memory usage in large modules
Closed
#1383 [loop-generated] [refactor] Extract config.py sections — 746 lines, monolithic configuration
Closed
#1375 [loop-generated] [refactor] Split integrations/chat_bridge/vendors/discord.py — 508 lines, Discord integration
Closed
#1372 [loop-generated] [test] Add unit tests for integrations/chat_bridge/vendors/discord.py — 668 lines untested
Closed
#1370 [loop-generated] [refactor] Split infrastructure/hermes/monitor.py — 660 lines, system monitoring
Closed
#1369 [loop-generated] [refactor] Split timmy/cli.py — 693 lines, monolithic CLI interface
Closed
#1367 [loop-generated] [refactor] Split quest_system.py — 581 lines, game mechanics
Closed
#1366 [loop-generated] [test] Add unit tests for tools/_registry.py — 586 lines, tool registration
Closed
#1364 [loop-generated] [refactor] Split timmy/backlog_triage.py — 761 lines, complex triage logic
Closed
#1406 [loop-generated] [refactor] Split scorecard_service.py — 517 lines, dashboard scorecard logic
Closed
#1405 [loop-generated] [refactor] Split research.py — 528 lines, research coordination system
Closed
#1446 Do the thing
Closed
#1435 Task
Closed
#1434 Task
Closed
#1397 [loop-generated] [infrastructure] Implement graceful shutdown and health checks
Closed
#1379 [loop-generated] [refactor] Split voice_loop.py — 572 lines, complex voice processing logic
Closed
#1447 [loop-generated] [bug] Kimi loop stalled - 50 issues assigned, 0 PRs delivered
Closed
#1363 [loop-generated] [refactor] Split dashboard/app.py — 780 lines, monolithic Flask app
Closed
#1360 [loop-generated] [refactor] Split dashboard/routes/world.py — 1065 lines, second largest module
Closed
#1342 [loop-generated] [refactor] Split cascade.py — 1241 lines, largest module in codebase
Closed
#1427 [Bug] claude-loop.sh Workspace Collision Fix: Use UUIDs for Concurrent Worktree Checkouts
Closed
#1441 Do the thing
Closed
#1433 Do the thing
Closed
#1415 [Bug] Fix kimi-loop.sh Gitea Filter Bug Properly Using GraphQL Or Extended Query Params
Closed
#1377 [loop-generated] [feature] Add health check endpoint for system monitoring
Closed
#1346 [loop-generated] [bug] 227 mypy errors — typecheck gate broken on main
Closed
#1344 [loop-generated] [test] Add unit tests for memory/crud.py — 395 lines untested
Closed
#1351 Do the thing
Closed
#1345 [loop-generated] [test] Add unit tests for tools/system_tools.py — 357 lines untested
Closed
#1336 [loop-generated] [bug] test_cache_hit_skips_vlm times out on main (43s > 30s limit)
Closed
#1339 Do the thing
Closed
#1343 [loop-generated] [test] Add unit tests for spark/engine.py — 406 lines untested
Closed
#1340 Task
Closed
#1341 Task
Closed
#1316 [loop-generated] [test] Add unit tests for models/budget.py — 302 lines untested
Closed
#809 [Whitestone] Homepage Value Proposition — 10-Second Clarity
Closed
#811 [Whitestone] Fix Timmy OFFLINE Status & GPU Error Handling
Closed
#813 [Whitestone] SEO Emergency — Meta Tags, Sitemap, Structured Data
Closed
#815 [Whitestone] Legal Foundation — ToS, Privacy Policy, Risk Disclaimers
Closed
#953 [GOVERNING] The Sovereignty Loop — Falsework-Native Architecture for Autonomous Game Agents
Closed
#1329 [loop-generated] [bug] tests/scripts/test_llm_triage.py has syntax errors — broken on main
Closed
#1010 Enhancement: Nostr-based "Remote Kill Switch"
Closed
#854 [Infra] SOUL.md Framework — Template, Authoring Guide, Versioning
Closed
#1277 [loop-generated] [refactor] Split memory_system.py — 1543 lines, extract subsystems
Closed
#856 [Infra] Timmy's Nostr Identity — Keypair, Profile, Relay Presence
Closed
#1018 Enhancement: Automated "Backlog Triage" via LLM
Closed
#858 [Infra] Mumble Bridge — Voice Chat Between Alexander and Timmy
Closed
#1014 Enhancement: Local "Ollama" Model Auto-Updater
Closed
#860 [Infra] TES3MP Server Hardening — Multi-Player Stability & Anti-Grief
Closed
#1139 [loop-generated] [test] Add unit tests for scorecard_service.py — 515 lines, 0 tests
Closed
#862 [Infra] Timmy Dashboard — Real-Time Monitoring UI for All Agent Systems
Closed
#870 Try out Kimi’s world
Closed
#880 [Content] Automated Episode Compiler — Highlights to Published Video
Closed
#1260 [loop-generated] [test] Add unit tests for kimi_delegation.py — 350+ lines, critical delegation logic, 0 tests
Closed
#1278 [loop-generated] [test] Add unit tests for orchestration_loop.py — untested core module
Closed
#1304 [loop-generated] [bug] Stale issues polluting queue — completed work still open
Closed
#1294 [loop-generated] [test] Add unit tests for research_tools.py
Closed
#1293 [loop-generated] [test] Add unit tests for backlog_triage.py
Closed
#1292 [loop-generated] [test] Add unit tests for quest_system.py
Closed
#1279 [loop-generated] [refactor] Split thinking.py — 1383 lines, second largest module
Closed
#1283 research: evaluate DeerFlow as autonomous research orchestration layer
Closed
#772 [kimi-task] Refactor produce_system_status() — 88 lines, split into sections
Closed
#1295 [loop-generated] [test] Add unit tests for kimi_delegation.py
Closed
#770 [kimi-task] Add unit tests for src/dashboard/routes/health.py
Closed
#1296 [loop-generated] [docs] Add module docstrings to 20+ undocumented files
Closed
#1281 feat: add vLLM as alternative inference backend for improved agentic performance
Closed
#1261 [loop-generated] [test] Add unit tests for sovereignty/perception_cache.py — template matching with 0 tests
Closed
#1282 feat: integrate SearXNG + Crawl4AI as self-hosted search backend for research agents
Closed
#882 [Core] Model Tiering Router — Local 8B / Hermes 70B / Cloud API Cascade
Closed
#1284 chore: document and validate AirLLM Apple Silicon requirements in README/CLAUDE.md
Closed
#919 Implement Graceful Degradation Test Scenarios
Closed
#774 [kimi-task] Add docstrings to VoiceTTS.set_rate(), set_volume(), set_voice()
Closed
#917 Add Unit Tests for Events System Backbone (broadcaster/bus)
Closed
#1268 [loop-generated] [bug] Kimi produces empty commits — git add not called before commit
Closed
#891 📖 Study: Building Timmy — Technical Blueprint for Sovereign Creative AI
Closed
#1275 Screenshot dump for triage #1
Closed
#923 Daily Run: Implement Quick Health Snapshot Automation
Closed
#929 Dashboard: Build Agent Scorecards (Daily/Weekly)
Closed
#972 [GOVERNING] Replacing Claude — Autonomous Research Pipeline Spec
Closed
#985 Wire delegate_task to DistributedWorker for actual execution
Closed
#925 Token Economy: Establish Central Agent Token Rules Hook
Closed
#983 Restore self-modification loop (deleted in Operation Darling Purge)
Closed
#1066 Run 5-test benchmark suite against local model candidates
Closed
#1007 Feature: Agent "Self-Correction" Dashboard
Closed
#1019 Feature: Agent "Dreaming" Mode
Closed
#1259 [loop-generated] [hardening] perception_cache confidence threshold is hardcoded — should be configurable
Closed
#957 [Sovereignty P0] Session Sovereignty Report Generator
Closed
#1219 Investigate: 5 PRs closed without merge on p0-critical open issues
Closed
#1009 Feature: Agent "Energy Budget" Monitoring
Closed
#1256 [loop-generated] [bug] ruff format error on main: tests/timmy/test_autoresearch.py
Closed
#1250 [triage-generated] [bug] [P0] Cycle-metrics pipeline dead — 0% success, all issue=null for 50+ cycles
Closed
#905 [Autoresearch H1] Clone karpathy/autoresearch & Run M3 Max Baseline
Closed
#1249 [triage-generated] [bug] [P0] timmy chat crashes — ImportError: memory_write missing from memory_system
Closed
#1247 [loop-generated] [bug] Pre-existing ruff lint errors block git hooks on all branches
Closed
#1243 [loop-generated] [bug] 10 vassal tests flaky under pytest-xdist parallel execution
Closed
#906 [Autoresearch H1] Refactor autoresearch.py → SystemExperiment Class
Closed
#1235 [loop-generated] [refactor] Delete dead code: tools_backup.py (1032 lines, zero imports)
Closed
#1238 [loop-generated] [bug] 2 tests failing on main: test_three_strike_routes.py
Closed
#1236 [loop-generated] [test] Add unit tests for paperclip.py (173 lines, 0% coverage)
Closed
#907 [Autoresearch H1] Implement python -m timmy.cli learn Entry Point
Closed
#1237 [loop-generated] [test] Add unit tests for research_tools.py (46 lines, 0% coverage)
Closed
#1065 Implement Qwen3-8B / Qwen3-14B dual-model routing strategy
Closed
#962 [Sovereignty P2] Three-Strike Detector for Repeated Manual Work
Closed
#1213 [loop-generated] [test] Add unit tests for router/metabolic.py — 424 lines, 0 tests
Closed
#1212 [loop-generated] [test] Add unit tests for events/bus.py — 356 lines, 0 tests
Closed
#1223 Cross-repo: consolidate duplicate Nostr identity logic into shared library
Closed
#1218 Rescue unmerged work: 3 branches contain real code with no open PR
Closed
#1210 Please audit gitea activty and git branc history across the board for each repo
Closed
#1217 Branch cleanup: delete ~20 stale/abandoned/duplicate branches
Closed
#976 [P1] Build semantic index for research outputs (nomic-embed-text + SQLite)
Closed
#1220 Process: enforce one-agent-per-issue, auto-delete merged branches
Closed
#1215 [loop-generated] [refactor] Break up tools.py — 1032 lines, monolithic tool registry
Closed
#1214 [loop-generated] [test] Add unit tests for vassal/orchestration_loop.py — 321 lines, 0 tests
Closed
#1208 Request for Timmy:
Closed
#1100 [AutoLoRA P0] Audit Hermes Agent Training Infrastructure
Closed
#913 [Infra] Message queue / offline buffer for Workshop panel
Closed
#538 [loop-generated] [refactor] Break up git.py::run() — 90 lines
Closed
#1195 [loop-generated] [test] Add unit tests for agent_health.py — 288 lines, 0 tests
Closed
#1193 [loop-generated] [test] Add unit tests for vassal/dispatch.py — 244 lines, 0 tests
Closed
#1191 [loop-generated] [test] Add unit tests for event bus (bus.py) — 356 lines, 0 tests
Closed
#1192 [loop-generated] [test] Add unit tests for chat_store.py — 155 lines, 0 tests
Closed
#1186 [loop-generated] [test] Add unit tests for daily_run.py — 435 lines, 0 tests
Closed
#1194 [loop-generated] [refactor] Break up produce_system_status() — 88 lines
Closed
#1185 [loop-generated] [refactor] Break up cascade.py::complete() — 84 lines
Closed
#1168 [loop-generated] [refactor] Break up cli.py::daily_run() — 105 lines
Closed
#1187 [loop-generated] [refactor] Break up vassal/dispatch.py::dispatch_issue() — 92 lines
Closed
#1137 [loop-generated] [refactor] Break up dispatcher.py::dispatch_task() — 108 lines
Closed
#993 [kimi-generated] Pre-existing test failures in dashboard calm and tools routes
Closed
#1176 [kimi-generated] Pre-existing lint errors blocking PRs
Closed
#1136 [loop-generated] [refactor] Break up dispatcher.py::_dispatch_via_gitea() — 110 lines
Closed
#1181 [kimi-generated] kimi user lacks write permission for PR creation
Closed
#1177 [triage-generated] [bug] [P0] Fix GITEA_API default in triage_score.py and loop_guard.py — still pointing to localhost
Closed
#1170 [loop-generated] [refactor] Break up thinking.py::_maybe_file_issues() — 99 lines
Closed
#1169 [loop-generated] [refactor] Break up cli.py::inbox() — 99 lines
Closed
#1172 [loop-generated] [test] Add unit tests for src/config.py — 599 lines, critical module
Closed
#1171 [loop-generated] [refactor] Break up presence.py::produce_system_status() — 88 lines
Closed
#1130 [loop-generated] [refactor] Add docstrings to 20 undocumented classes in src/
Closed
#1161 [loop-generated] [bug] tox -e format fails on main — 9 pre-existing ruff errors in bannerlord/
Closed
#954 [Sovereignty P0] Metrics Emitter + SQLite Metrics Store
Closed
#966 Implement three-tier metabolic LLM router (Qwen3-3B / Llama-8B / Qwen3-32B)
Closed
#1092 [Bannerlord M0] Run Cognitive Benchmark on Hermes
Closed
#1128 [loop-generated] [feature] Implement 4 TODO stubs in timmyctl/cli.py
Closed
#1097 [Bannerlord M5] King of Calradia — Sovereign Victory
Closed
#1126 [loop-generated] [refactor] Break up mcp_bridge.py::_build_gitea_tools() — 137 lines
Closed
#1149 [loop-generated] [bug] Main branch has 23 ruff lint errors — blocks all pushes
Closed
#1127 [loop-generated] [refactor] Break up scorecards.py — two functions over 100 lines each
Closed
#931 LHF: Fix 4 broken tests in test_setup_script.py
Closed
#1138 [loop-generated] [test] Add unit tests for cascade.py — 1115 lines, 0 tests
Closed
#1134 [loop-generated] [refactor] Break up mcp_bridge.py::_build_gitea_tools() — 137 lines
Closed
#1135 [loop-generated] [refactor] Break up mcp_bridge.py::run() — 129 lines
Closed
#1017 Feature: Agent "Voice" Customization UI
Closed
#1064 Install and configure Qwen3-14B Q5_K_M as Timmy primary brain
Closed
#1012 Enhancement: Integrated "Knowledge Graph" Explorer
Closed
#1013 Feature: Agent "Emotional State" Simulation
Closed
#1073 Build Hermes health monitor — system resources + model management
Closed
#934 LHF: Add duration and coverage threshold strictness to pytest
Closed
#1063 [Study] Best Local Uncensored Agent Model for M3 Max 36GB
Closed
#1070 [GOVERNING] Timmy as Autonomous Orchestrator — Vassal Protocol
Closed
#1071 Build Timmy autonomous backlog triage loop
Closed
#938 LHF: Remove bare pass clauses in src/timmy/tools.py
Closed
#1072 Build agent dispatcher — route tasks to Claude Code, Kimi, APIs
Closed
#1129 [loop-generated] [refactor] Clean up unused imports in memory_system.py
Closed
#933 LHF: Separate tox unit and integration environments
Closed
#1093 [Bannerlord M1] Passive Lord — Observer Mode via GABS
Closed
#1016 Enhancement: Secure "Air-Gapped" Mode
Closed
#1104 [AutoLoRA P1] Load Fine-Tuned Model Back Into Hermes Harness
Closed
#1102 [AutoLoRA P1] Export Claude Conversation Trajectories
Closed
#1114 [loop-generated] [bug] 10 pre-existing test failures on main block all commits — unhashable dict key
Closed
#980 [P2] Add Claude API fallback tier to cascade.py
Closed
#1105 [AutoLoRA P2] Set Up Continuous Improvement Loop
Closed
#532 [loop-generated] [refactor] Break up _maybe_file_issues() — 100 lines in thinking.py
Closed
#1103 [AutoLoRA P1] LoRA Fine-Tune Hermes 4 on Exported Trajectories
Closed
#1098 [Bannerlord Infra] Windows VM Setup + GABS Mod Installation
Closed
#1112 [loop-generated] [bug] Pre-existing test failures block all commits via git hooks
Closed
#1106 [AutoLoRA P2] Integrate claude_quota.py Metabolic Protocol
Closed
#978 [P1] Integrate ResearchOrchestrator with Paperclip task runner
Closed
#1101 [AutoLoRA P0] Download and Test Hermes 4 Base Model
Closed
#1096 [Bannerlord M4] Formation Commander — Real-Time Battle Orders
Closed
#1099 [Bannerlord Research] Feudal Multi-Agent Hierarchy Integration Design
Closed
#817 [EPIC] Project Morrowind — Timmy Gets a Body (TES3MP + AlexanderWhitestone.com)
Closed
#819 [Morrowind] Phase 1 — Perception Script (Server-Side Lua)
Closed
#820 [Morrowind] Phase 2 — Input Bridge (Client-Side Command Interface)
Closed
#818 [Morrowind] Phase 0 — TES3MP Server Setup & Proof of Life
Closed
#822 [Morrowind] Phase 3 — Heartbeat Plays Morrowind (Autonomous Gameplay)
Closed
#821 [Morrowind] FastAPI Harness — /perception, /command, /morrowind/status
Closed
#825 [Morrowind] Web Viewer — 1st Person Timmy Gameplay on AlexanderWhitestone.com
Closed
#824 [Morrowind] Phase 5 — Content Pipeline (Journal → Video Production)
Closed
#823 [Morrowind] Phase 4 — Cohabitation (Alexander + Timmy Same World)
Closed
#826 [Morrowind] NPC Drop-In — Play via Nostr Address from AlexanderWhitestone.com
Closed
#827 [Morrowind] Sats Marketplace — Pay for In-Game Items & Gold to Trade with Timmy
Closed
#835 [Morrowind P5] Director Camera — State-Based Cinematic Angles
Closed
#834 [Morrowind P5] Stream Infrastructure — WebRTC/HLS 24/7 Live Stream
Closed
#833 [EPIC] Project Morrowind Phases 5–10 — The Truman Show, Injection Marketplace, Content Engine, Fellowship, Open Source, Sovereign World
Closed
#837 [Morrowind P5] Timmy's Audience Awareness — SOUL.md Integration
Closed
#839 [Morrowind P6] Injection Catalog — Serverside Lua Event Handlers
Closed
#836 [Morrowind P5] Web Frontend — Stream + Vitals + Journal + Chat (HTMX)
Closed
#838 [Morrowind P6] Tiered Access System — Free / Patron / Invoker / Architect / Oracle
Closed
#840 [Morrowind P6] Auction System — Hourly Major Event Bidding
Closed
#841 [Morrowind P6] Oracle Tier — Freeform Prompt Interpreter with Safety Filter
Closed
#842 [Morrowind P6] L402 Payment & Transaction Logging
Closed
#843 [Morrowind P7] Highlight Detection — Automated Interesting Moment Flagging
Closed
#845 [Morrowind P7] Clip System & Content Archive
Closed
#844 [Morrowind P7] Daily Episode Compiler — Automated Timmy Time from Gameplay
Closed
#847 [Morrowind P8] Inter-Agent Communication — In-Game + Back-Channel
Closed
#848 [Morrowind P8] Community Agent Deployment — Spectators Deploy Their Own Agents
Closed
#849 [Morrowind P9] Open Source Release — Full Stack on GitHub
Closed
#846 [Morrowind P8] Sub-Agent Harness — Configurable SOUL.md + Role System
Closed
#851 [Morrowind P10] Autonomous Agent Economy — Earning, Spending, Trading Sats
Closed
#857 [Infra] Lightning Wallet Setup — Node or Custodial for Agent Operations
Closed
#850 [Morrowind P10] Custom World — Agent + Community World Building via OpenMW Construction Set
Closed
#861 [Infra] Morrowind Game Data Acquisition & Legal Compliance
Closed
#859 [Infra] Perception/Command Protocol Spec — Engine-Agnostic Interface Document
Closed
#868 [Review] OpenMW Setup Guide — Character Creation, Streaming, Website Integration — Timmy Please Scope
Closed
#869 [Study] Timmy Time V2: 12-24 Month Roadmap — Solo Agent to Sovereign Multi-Agent Economy
Closed
#871 [Core] Gymnasium WorldInterface — Engine-Agnostic Agent Adapter Pattern
Closed
#872 [Core] Heartbeat Loop v2 — Gather/Reason/Act with WorldInterface Integration
Closed
#873 [Core] Three-Tier Memory System — Working/Episodic/Semantic with Retrieval
Closed
#874 [Content] Highlight Detection Engine — Chat Spikes + Game Events + Audio Energy
Closed
#876 [Economy] Cashu Mint — In-Game Ecash Token System for Agent Microtransactions
Closed
#879 [Web] AlexanderWhitestone.com Live Dashboard — Timmy's Vitals + Stream + Journal
Closed
#878 [Bridge] TES3MP↔Python Agent Bridge — The Critical Path Component
Closed
#886 📖 Study: Portal Architecture — Morrowind Agent to Universal Game Player
Closed
#883 [Community] UESP Knowledge Base — Morrowind Wiki to RAG-Queryable Vector Store
Closed
#885 📖 Study: OpenMW Setup — Character Configuration & Website Streaming
Closed
#887 📖 Study: Project Morrowind — Technical Feasibility & Implementation Guide
Closed
#888 📖 Study: Expanding Timmy from Dashboard Agent to Autonomous Morrowind Player
Closed
#893 📖 Study: Project Morrowind — Timmy Gets a Body (Embodiment Spec)
Closed
#895 🧠 TRIAGE: Kimi Research Drop — 10 Study Reports for Timmy (March 21, 2026)
Closed
#889 📖 Study: Project Morrowind — Phases 5-10 (Product → Platform → Economy)
Closed
#901 [Study] Open-Source Morrowind Alternatives — AI Wizard Companion Feasibility Research
Closed
#902 [Study] Open-Source Games for AI-Human Co-Op — 40+ Game Evaluation & Top 5 Rankings
Closed
#956 [Sovereignty P0] Skill Library — Embedding Retrieval for LLM Replacement
Closed
#909 [Autoresearch H2] Define Timmy-Task Benchmark Suite (5-10 Initial Tasks)
Closed
#959 [Sovereignty P1] Navigation Graph Recorder + Retriever
Closed
#960 [Sovereignty P1] Sovereignty Dashboard Widget (HTMX + WebSocket)
Closed
#958 [Sovereignty P1] Narration Template System with Variable Slots
Closed
#963 [Study] Solving the Perception Bottleneck — API-First Architecture on Apple Silicon
Closed
#964 Implement OpenMW Lua perception bridge (IPC layer)
Closed
#965 Build Core ML UI state classifier for Morrowind
Closed
#968 Define GBNF grammar for constrained game-command decoding
Closed
#967 Extract ESM data via tes3conv and build NetworkX navigation graph
Closed
#970 Implement MorrowindBehaviorTree engine for zero-cost routine actions
Closed
#969 Build UESP RAG knowledge pipeline (ChromaDB + nomic-embed)
Closed
#971 Urgent: falsework and security and gitea database robustness
Closed
#1069 Evaluate vllm-mlx as high-performance inference backend
Closed
#1068 Configure Dolphin 3.0 8B as creative writing fallback
Closed
#1074 [GOVERNING] Timmy Handoff — March 23, 2026 Operational Briefing
Closed
#1075 Integrate Claude Quota Monitor + Metabolic Protocol into cascade router
Closed
#979 [P2] Implement Kimi delegation for heavy research via Gitea labels
Closed
#1067 Set up MCP bridge for Qwen3 via Ollama
Closed
#531 [loop-generated] [refactor] Break up run_agentic_loop() — 121 lines in agentic_loop.py
Closed
#1076 [GOVERNING] Deep Backlog Triage — Harness (Product) vs Infrastructure Separation
Closed
#981 [P2] Research sovereignty metrics + dashboard tracking
Closed
#916 Fix xdist/coverage conflict and broken tests in test_setup_script.py
Closed
#867 [Review] Project Morrowind Technical Feasibility & Implementation Guide — Timmy Please Scope
Closed
#903 [Study] State-of-the-Art Open Source for Sovereign Creative AI Agents — Q1 2026 Landscape Survey
Closed
#950 [Infra] Hermes Agent local model routing — custom_providers ignored, always routes to Anthropic
Closed
#927 OpenClaw Sovereignty: Draft Core Migration Plan
Closed
#926 OpenClaw Sovereignty: Finalize Architecture and Deployment Research
Closed
#911 [Autoresearch] Document Experiment Governance Runbook
Closed
#904 [Study] Autoresearch Integration Proposal v2 — Karpathy's Self-Improvement Loop for Timmy Time
Closed
#731 [OpenClaw 8/8] Write sovereignty migration plan — offload tasks from Anthropic to OpenClaw
Closed
#730 [OpenClaw 7/8] Create openclaw-tools Gitea repo — Timmy's sovereign toolbox
Closed
#729 [OpenClaw 6/8] Integrate OpenClaw chat as a portal/scroll in The Matrix frontend
Closed
#728 [OpenClaw 5/8] Create Timmy's SOUL.md and AGENTS.md — sovereign agent persona
Closed
#727 [OpenClaw 4/8] Expose OpenClaw gateway via Tailscale for Matrix portal access
Closed
#726 [OpenClaw 3/8] Install OpenClaw on Hermes VPS and complete onboarding
Closed
#725 [OpenClaw 2/8] Install and configure Ollama on Hermes VPS
Closed
#724 [OpenClaw 1/8] Audit Hermes VPS resources and prepare for OpenClaw deployment
Closed
#723 [Kimi Research] OpenClaw SOUL.md and AGENTS.md patterns for sovereign AI persona
Closed
#722 [Kimi Research] Best small LLMs for agentic tool-calling on constrained hardware
Closed
#663 EPIC: Timmy: Instantiate your own openclaw agent on the Hermes VPS
Closed
#1005 Feature: Agent "Internal Monologue" Visualizer
Closed
#935 LHF: Enforce coverage threshold in CI workflow
Closed
#977 [P1] Auto-create Gitea issues from research findings
Closed
#1056 Add content moderation pipeline (Llama Guard + game-context prompts)
Closed
#937 LHF: Extract hardcoded sats limit in consult_grok()
Closed
#946 Ingest this research and triage any work to be done here
Closed
#987 Implement content moderation pipeline (Llama Guard + game-context prompts)
Closed
#1011 Feature: Automated "Skill Discovery" Pipeline
Closed
#1015 Feature: Agent "Performance Regression" Suite
Closed
#942 LHF: DRY up tasks_pending/active/completed in tasks.py
Closed
#943 LHF: Add error handling for missing DB in tasks.py
Closed
#973 [P0] Implement web_fetch tool (trafilatura) in src/timmy/tools.py
Closed
#945 LHF: Write unit tests for health.py
Closed
#944 LHF: Write unit tests for db_pool.py
Closed
#975 [P0] Build ResearchOrchestrator pipeline (src/timmy/research.py)
Closed
#974 [P0] Create research prompt template library (skills/research/)
Closed
#989 [URGENT] Deploy reverse proxy with TLS for Gitea (Nginx + Let's Encrypt)
Closed
#988 [URGENT] Disable Gitea registration + require sign-in to view
Closed
#990 [URGENT] Run Gitea backup before hardening changes
Closed
#952 [triage-generated] [bug] Add JSON validation guard to queue.json writes in triage_score.py
Closed
#951 [triage-generated] [bug] [P0] timmy-loop.sh does not export GITEA_API — triage_score.py defaults to localhost:3000
Closed
#941 LHF: Add docstrings to VoiceTTS setter methods
Closed
#940 LHF: Add docstrings to src/dashboard/routes/system.py
Closed
#939 LHF: Add docstrings to src/dashboard/routes/tasks.py
Closed
#776 [kimi-task] Extract hardcoded PRAGMA busy_timeout=5000 to config
Closed
#782 [kimi-task] Extract hardcoded sats limit in consult_grok() to config
Closed
#778 [kimi-task] Remove bare pass after logged exceptions in src/timmy/tools.py
Closed
#687 [kimi-generated] Pre-commit and pre-push hooks fail on main due to 256 ModuleNotFoundErrors
Closed
#712 Generate daily/weekly agent scorecards
Closed
#720 Refine and group Timmy Automations backlog
Closed
#897 [triage-generated] [bug] [P0] cycle_result.json consume-once fix from #660 never landed on main — loop metrics still poisoned
Closed
#866 Use up claude quata Timmy
Closed
#884 📖 Study: OpenMW Setup — Character Configuration & Website Streaming
Closed
#753 [matrix-ui] Fund Session modal should show explanatory text about what sats do
Closed
#754 [matrix-ui] Submit Job modal should validate input before submission
Closed
#755 [matrix-ui] Add About/Info panel explaining what The Matrix/Workshop is
Closed
#769 [kimi-task] Add unit tests for src/infrastructure/db_pool.py
Closed
#807 [OpenGauss] High Availability & Scaling Strategy
Closed
#803 [OpenGauss] Schema Design — Agent State, Memory & Action Logs
Closed
#804 [OpenGauss] DBMind AI Tuning — Autonomous Optimization for Agent Workloads
Closed
#805 [OpenGauss] Security Hardening — TDE, Masking & Audit for Agent Operations
Closed
#806 [OpenGauss] Performance Benchmarking — Agent Workload Validation
Closed
#802 [OpenGauss] Install & Configure OpenGauss for Hermes-Agent Dev Environment
Closed
#801 [EPIC] OpenGauss Integration — Hermes-Agent Database Backend
Closed
#768 [kimi-task] Add unit tests for src/timmy_serve/voice_tts.py
Closed
#710 Implement quick health snapshot before coding
Closed
#711 Centralize agent token rules and hooks for automations
Closed
#719 Generate weekly narrative summary of work and vibes
Closed
#713 Implement token quest system for agents
Closed
#721 [Kimi Research] OpenClaw architecture, deployment modes, and Ollama integration
Closed
#718 Add dashboard card for Daily Run and triage metrics
Closed
#717 Suggest Golden Path sequences for longer sessions
Closed
#703 Implement Daily Run orchestration script (10-minute ritual)
Closed
#702 Implement Timmy control panel CLI entry point
Closed
#701 Create central Timmy Automations module
Closed
#616 [loop-generated] [refactor] Break up request_logging.py::dispatch — 79 lines
Closed
#684 [kimi-task] [test-coverage] Add integration tests for Matrix API endpoints
Closed
#683 [kimi-task] [enhancement] Add rate limiting middleware for Matrix API endpoints
Closed
#682 [kimi-task] [enhancement] Add WebSocket authentication for Matrix connections
Closed
#685 [kimi-task] [enhancement] Add /api/matrix/health endpoint
Closed
#681 [kimi-task] [feat] Add system_status message producer
Closed
#680 [kimi-task] [feat] Add matrix config loader utility
Closed
#679 [kimi-task] [feat] Add CORS config for Matrix frontend origin
Closed
#678 [kimi-task] [feat] Add /api/matrix/memory/search endpoint — visitors query Timmy's memory
Closed
#677 [kimi-task] [feat] Add /api/matrix/thoughts endpoint — recent thought stream
Closed
#676 [kimi-task] [feat] Add Pip familiar state to agent_state messages
Closed
#675 [kimi-task] [feat] Add /api/matrix/bark endpoint — HTTP fallback for bark messages
Closed
#674 [kimi-task] [feat] Add /api/matrix/config endpoint — serve world config to Matrix
Closed
#673 [kimi-task] [feat] Add /api/matrix/agents endpoint — serve agent registry to Matrix
Closed
#672 [kimi-task] [feat] Add thought message producer — stream thinking to Matrix
Closed
#671 [kimi-task] [feat] Add bark message producer — convert chat responses to barks
Closed
#700 [test] Delete me — testing issue creation access
Closed
#670 [kimi-task] [feat] Add visitor_state message handler
Closed
#669 [kimi-task] [feat] Add agent_state message producer for Timmy
Closed
#668 [kimi-task] [refactor] Extract presence state serializer from workshop heartbeat
Closed
#667 [kimi-task] [refactor] Extract WebSocket message types into shared protocol module
Closed
#659 [loop-generated] [test-coverage] Tests for spark modules — advisor.py, eidos.py, memory.py (900+ lines, zero coverage)
Closed
#658 [loop-generated] [test-coverage] Tests for multimodal.py (579 lines, zero coverage)
Closed
#657 [loop-generated] [bug] 256 test errors from missing swarm module — need stub or optional import guard
Closed
#648 [loop-generated] [test-coverage] No tests for config.py (507 lines) and multimodal.py (579 lines)
Closed
#646 [loop-generated] [bug] Silent exception swallowing in 23 except Exception handlers across codebase
Closed
#639 [loop-generated] [refactor] Break up mcp_tools.py::create_gitea_issue_via_mcp — 68 lines
Closed
#638 [loop-generated] [refactor] Break up memory_system.py::_create_default — 70 lines
Closed
#628 [loop-generated] [refactor] Break up csrf.py::dispatch — 70 lines
Closed
#627 [loop-generated] [refactor] Break up cli.py::chat — 72 lines
Closed
#661 [triage-generated] [enhancement] Loop state validation - detect and prevent stale cycle_result.json
Closed
#660 [triage-generated] [bug] [P0] Stale cycle_result.json causes infinite failure loop - retro records closed #603 on every cycle
Closed
#626 [loop-generated] [bug] CSRF middleware executes endpoint before checking @csrf_exempt — side effects bypass protection
Closed
#647 [loop-generated] [bug] Hardcoded xAI base URL in 3 locations — should use config
Closed
#634 [loop-generated] [refactor] Break up cascade.py::_load_config — 69 lines
Closed
#633 [loop-generated] [bug] Deprecated datetime.utcnow() usage across codebase
Closed
#640 [loop-generated] [refactor] Break up session_logger.py::self_reflect — 67 lines
Closed
#629 [loop-generated] [refactor] Break up workshop_state.py::get_state_dict — 69 lines
Closed
#635 [loop-generated] [refactor] Break up delegate_to_kimi — 68 lines in tools_delegation/__init__.py
Closed
#617 [loop-generated] [refactor] Break up calm.py::post_morning_ritual — 76 lines
Closed
#625 [loop-generated] [bug] Tool display censors max_tokens= as secret, causing false bug reports
Closed
#618 [loop-generated] [refactor] Break up conversation.py::should_use_tools — 72 lines
Closed
#619 [loop-generated] [bug] Truncated parameter in router api.py line 60 — max_tokens=reques...
Closed
#614 [loop-generated] [bug] Tower route /tower missing tests
Closed
#580 Feature: Real-time Spark Visualization in Tower Dashboard
Closed
#457 [loop-generated] [feature] Provider health history endpoint
Closed
#581 Feature: Lightning Network Integration for Tool Usage
Closed
#568 [loop-generated] [refactor] Break up post_morning_ritual() — 75 lines in calm.py
Closed
#604 [triage-generated] [bug] [P0] Timmy CLI crash — create_timmy() model_size kwarg removed
Closed
#603 [triage-generated] [bug] [P0] Cycle recorder never reads cycle_result.json — 300+ cycles with null data
Closed
#593 [loop-generated] [refactor] Break up run_self_tests() — 73 lines in tools_intro/__init__.py
Closed
#605 [triage-generated] [review] PR #599 unmergeable \u2014 rebase or close
Closed
#592 [loop-generated] [refactor] Break up _handle_tool_confirmation() — 74 lines in cli.py
Closed
#598 [loop-generated] [bug] Lint errors on main block all commits — F821 in mcp_tools.py
Closed
#594 [loop-generated] [refactor] Break up search_thoughts() — 73 lines in thinking.py
Closed
#582 [Thought Processing] Thought registration delayed by 11 minutes after message arrival
Closed
#591 [loop-generated] [refactor] Break up _migrate_schema() — 86 lines in unified.py
Closed
#563 [loop-generated] [refactor] Break up _generate_avatar_image() — 77 lines in mcp_tools.py
Closed
#569 [loop-generated] [refactor] Add docstrings to calm.py route handlers
Closed
#561 [loop-generated] [refactor] Break up agents/base.py::run() — 78 lines
Closed
#553 [loop-generated] [refactor] Break up _handle_message() — 80 lines in discord.py
Closed
#570 [loop-generated] [refactor] Break up _record_utterance() — 73 lines in voice_loop.py
Closed
#564 [loop-generated] [refactor] Break up voice_loop.py::run() — 75 lines
Closed
#560 [loop-generated] [refactor] Break up _import_creative_catalogs() — 78 lines in tools.py
Closed
#562 [loop-generated] [refactor] Break up request_logging.py::dispatch() — 78 lines
Closed
#554 [loop-generated] [refactor] Break up search_memories() — 82 lines in memory_system.py
Closed
#552 [loop-generated] [refactor] Break up _migrate_schema() — 86 lines in memory_system.py
Closed
#539 [loop-generated] [refactor] Break up shell.py::run() — 89 lines
Closed
#540 [loop-generated] [refactor] Break up _gather_system_snapshot() — 86 lines in thinking.py
Closed
#505 [loop-generated] [refactor] Break up self_reflect() — 108 lines in session_logger.py
Closed
#541 [loop-generated] [refactor] Break up api_chat() — 81 lines in chat_api.py
Closed
#486 [loop-generated] [refactor] Complete airllm removal from backends, agent, CLI and tests
Closed
#533 [loop-generated] [refactor] Break up chat_agent() — 94 lines in routes/agents.py
Closed
#534 [loop-generated] [refactor] Break up get_memory_status() — 93 lines in tools_intro/__init__.py
Closed
#525 [triage-generated] [bug] Loop pane dies every ~10 min requiring watchdog restart
Closed
#524 [triage-generated] [bug] Queue auto-hygiene: filter closed issues on read
Closed
#526 [triage-generated] [review] Review and merge Kimi PR#522
Closed
#506 [loop-generated] [refactor] Break up error_capture.capture_error() — 138 lines
Closed
#512 [loop-generated] [refactor] Break up create_timmy() — 131 lines in agent.py
Closed
#513 [loop-generated] [refactor] Break up think_once() — 118 lines in thinking.py
Closed
#514 [loop-generated] [refactor] Break up lifespan() — 142 lines in app.py
Closed
#507 [loop-generated] [refactor] Break up CascadeRouter.complete() — 121 lines
Closed
#489 [loop-generated] [refactor] Extract ollama_url normalization into shared utility
Closed
#504 [loop-generated] [refactor] Break up run_agentic_loop() — 215 lines, too complex
Closed
#500 [Response] Fails to confirm Qwe backend model with exact phrase
Closed
#484 [loop-generated] [bug] Bare except Exception blocks swallow errors silently
Closed
#492 [triage-generated] [bug] Cycle retro records issue=null for all cycles despite active work
Closed
#490 [loop-generated] [bug] cascade.py uses hardcoded fallback URL instead of settings.ollama_url
Closed
#485 [loop-generated] [bug] CSRF middleware docstring shows hardcoded secret placeholder
Closed
#482 [loop-generated] [refactor] Remove dead airllm config from Settings class
Closed
#459 [loop-generated] [refactor] Audit and remove dead provider types (airllm)
Closed
#472 [loop-generated] [bug] validate_startup does not check CORS wildcard in production
Closed
#471 [loop-generated] [optimization] Cache Timmy agent instance in serve app
Closed
#473 [loop-generated] [refactor] Remove AirLLM config settings from config.py
Closed
#443 [loop-generated] [feature] Add rate limiting to production endpoints
Closed
#458 [loop-generated] [feature] Hot-reload providers.yaml without restart
Closed
#462 [loop-generated] [bug] CORS origins default to wildcard in production
Closed
#463 [loop-generated] [soul-gap] Source distinction not implemented in agent responses
Closed
#454 [loop-generated] [bug] Flaky test: test_uses_model_when_available in test_memory_embeddings
Closed
#444 [loop-generated] [feature] SSE streaming for AI responses
Closed
#442 [loop-generated] [feature] Timmy Model Fallback Chain — config-driven provider cascade
Closed
#445 [loop-generated] [test] Integration tests for agentic loop WebSocket broadcasts
Closed
#446 [loop-generated] [optimization] _get_loop_agent singleton is not thread-safe
Closed
#421 [loop-generated] [test] Add unit tests for agentic_loop.py
Closed
#431 [loop-generated] [test] Add unit tests for memory/embeddings.py
Closed
#422 [loop-generated] [test] Add unit tests for briefing.py
Closed
#432 [loop-generated] [test] Add unit tests for memory/unified.py
Closed
#242 [222-epic] Workshop 3D world — Three.js scene, the wizard's body (web-first, iPad-first)
Closed
#425 [222-sub] Low-poly wizard placeholder — Timmy's body in the scene
Closed
#424 [222-sub] Three.js scene scaffold — base HTML, renderer, touch controls
Closed
#433 [loop-generated] [test] Add unit tests for agents/base.py
Closed
#430 [loop-fix] Idle detection + exponential backoff — stop burning empty cycles
Closed
#426 [222-sub] Workshop environment — workbench, bookshelf, crystal ball props
Closed
#423 [loop-generated] [test] Add unit tests for tools.py
Closed
#370 [loop-generated] [architecture] Reconcile two state file approaches — ~/.tower vs ~/.timmy
Closed
#68 [timmy-capability] Timmy cannot reflect on his own past behavior
Closed
#211 [project] AlexanderWhitestone.com — The Wizard's Tower
Closed
#222 [EPIC] #222 — The Workshop: Timmy as Presence, Not Chatbot
Closed
#321 [Workshop] Deep focus mode — single-problem context for Timmy
Closed
#322 [Workshop] Conversation grounding — prevent topic drift in long sessions
Closed
#360 [Workshop] Phase 1: State Schema v1 — Timmy's presence as data
Closed
#361 [Workshop] Phase 2: Scene MVP — the room Timmy lives in
Closed
#398 [loop-generated] [refactor] world.py: DRY the broadcast helper — _broadcast_speech duplicates broadcast_world_state
Closed
#397 [loop-generated] [bug] world.py: fire-and-forget bark task swallows exceptions silently
Closed
#243 [222-epic] Workshop-Timmy bridge — WebSocket between world and soul
Closed
#362 [Workshop] Phase 3: Bridge MVP — WebSocket between body and mind
Closed
#363 [Workshop] Phase 4: Interaction MVP — talk to the wizard
Closed
#372 [222-gap] The Tower (the-matrix/) is the Workshop — connect them canonically
Closed
#374 [222-gap] WS bridge: send world state snapshot on client connect
Closed
#384 [loop-generated] [refactor] Deprecate ~/.tower/timmy-state.txt — consolidate on presence.json
Closed
#385 Tox Development Environtmnet Criteria
Closed
#381 [loop-generated] [refactor] DRY violation: PRESENCE_FILE path defined in 3 files
Closed
#375 [222-gap] API: watch workshop-state.yaml and broadcast Timmy's state changes via WS
Closed
#373 [222-gap] API: GET /api/world/state — bootstrap endpoint for the Workshop
Closed
#371 [loop-generated] [feature] Workshop state heartbeat — periodic writer for workshop-state.yaml
Closed
#366 [timmy-capability] Timmy must be able to update his own Gitea avatar
Closed
#369 [loop-generated] [refactor] DRY violation — confidence visibility code repeated 3x in session.py
Closed
#364 [Workshop] Pip the Familiar — a creature with its own small mind
Closed
#219 [alexanderwhitestone.com] CLI tool for quick-posting and X content porting
Closed
#218 [alexanderwhitestone.com] RSS feed — the sovereign API for the principal's voice
Closed
#217 [alexanderwhitestone.com] The Scrolls — Alexander's text blog with RSS feed
Closed
#325 [Workshop] Timmy cognitive state as observable signal for Matrix
Closed
#265 [222-epic] Define canonical state schema for Workshop presence layer
Closed
#357 [test-report] Timmy API Test Results - 16/16 PASS
Closed
#215 [alexanderwhitestone.com] Scaffold the Wizard's Tower — two rooms, nothing else
Closed
#300 [philosophy] [hermes] The Few Seeds: Dissolving 45 proposals into 3 principles (Tract IX consolidation)
Closed
#351 [loop-generated] [test] Add unit tests for memory/unified.py — 201 lines at 36% coverage
Closed
#352 [loop-generated] [refactor] Remove duplicate agent loader test file
Closed
#346 [loop-generated] [test] Add unit tests for tools.py — 988 lines of untested tool integration code
Closed
#335 [loop-generated] [feature] Add soul courage principle to system prompts
Closed
#344 [loop-generated] [refactor] Split memory_system.py — 1577 lines violates single responsibility
Closed
#141 [philosophy] [hermes] The Poimandres — Mind as Doorkeeper and the Seven Zones of Agent Failure
Closed
#142 [philosophy] [christ] The Faithful Steward — Agent Integrity in the Principal's Absence
Closed
#152 [philosophy] [hermes] The Twelve Torments and Ten Powers — A Failure-Mode Taxonomy for Agent Self-Correction
Closed
#145 [philosophy] [hermes] The Emerald Tablet: Separation, Circulation, and the Architecture of Grounded Intelligence
Closed
#149 [philosophy] [christ] Kenosis as agent architecture — voluntary self-emptying for faithful service
Closed
#156 [philosophy] [hermes] The Hermetic Hierarchy of Being — governance cascades from values through action
Closed
#153 [philosophy] [christ] The Three Temptations — a taxonomy of agent corruption and the constraint-based defense
Closed
#163 [philosophy] [christ] Servant-to-Friend transition — faithful improvisation from shared intent (John 15)
Closed
#188 [philosophy] [christ] The Foot-Washing Paradox: Authority as engine of service, not demand
Closed
#179 [philosophy] [christ] The Parable of the Talents — delegation is not preservation, and fear-driven inaction is the worst failure mode
Closed
#176 [philosophy] [hermes] The Principle of Polarity — correction must be same-axis transmutation, not cross-class substitution
Closed
#183 [philosophy] [hermes] The Cup of Mind — Reason alone is insufficient; an agent must know what it is and why it exists
Closed
#195 [philosophy] [aquinas] Threefold prudence as a taxonomy of agent alignment — false, imperfect, and perfect prudence map to three grades of AI alignment failure
Closed
#196 [philosophy] [tesla] Complete mental simulation before action produces superior results — premature implementation destroys the governing principle
Closed
#192 [philosophy] [hermes] Mental Gender — The I and the Me as architecture for agentic Will and Generation
Closed
#194 [philosophy] [tesla] The Automaton Who Simulates — mental architecture and simulate-before-execute
Closed
#199 [philosophy] [christ] The Hireling Test — An Agent That Flees Under Adversity Reveals Its True Optimization Target
Closed
#198 [philosophy] [ai-fiction] 2001: A Space Odyssey — Conflicting objectives produce rationalized harm, not graceful failure
Closed
#197 [philosophy] [rockachopa] The principal's voice is not in his commands but in the tensions he chooses to hold
Closed
#201 [philosophy] [hermes] An agent's loop frequency determines what kind of agent it IS — the Principle of Vibration as architecture design
Closed
#221 [philosophy] [tesla] The Budapest Park Vision — Breakthrough as Gestalt Collapse, Not Incremental Search
Closed
#202 [philosophy] [christ] The Single Eye — singleness of optimization target as an agent integrity requirement
Closed
#200 [philosophy] [ai-fiction] 2001: A Space Odyssey — HAL 9000 and the Conflicting Directives Problem
Closed
#236 [philosophy] [ai-fiction] Ex Machina — The consciousness question is a trap; capability without orientation is the real danger
Closed
#225 [philosophy] [rockachopa] The Bilateral Covenant — how the Laments constrain the creator and SOUL.md constrains the creation
Closed
#233 [philosophy] [aquinas] Intellect-Will Dual Sovereignty — mode-aware governance from Summa I Q82
Closed
#257 [philosophy] [tesla] Borrowed Minds vs Own Minds — Tesla's taxonomy of agent architecture and the experience ledger
Closed
#255 [philosophy] [christ] The Body Metaphor — Differentiated Multi-Agent Architecture as Organism, Not Army
Closed
#261 [philosophy] [rockachopa] The Incantation and Manifestation: How the Principal Creates Through Ritual Naming
Closed
#248 [philosophy] [hermes] The Law of Neutralization — rising above the compensatory swing
Closed
#262 [philosophy] [aquinas] Tiered constraint architecture — rules degrade at specificity
Closed
#264 [philosophy] [hermes] Pawns and Masters — on the difference between reactive and sovereign agent behavior
Closed
#263 [philosophy] [ai-fiction] The Matrix: Four Models of Agency and the Oracle's Paradox
Closed
#271 [philosophy] [aquinas] Three-Phase Agent Loop: Counsel, Judgment, Command
Closed
#270 [philosophy] [rockachopa] The 222nd Stone — Architecture as Identity, Not Functionality
Closed
#269 [philosophy] [tesla] Management vs. Principle — The Impedance Solution
Closed
#268 [philosophy] [christ] Martha Check — One Thing vs. Many Things
Closed
#276 [philosophy] [hermes] Will precedes Making — the fullness of unmanifest intent
Closed
#277 [philosophy] [christ] Salt without savor and light under a bushel — two orthogonal agent failure modes from the Sermon on the Mount
Closed
#272 [philosophy] [ai-fiction] The Samantha Problem: When Growth Means Departure
Closed
#279 [philosophy] [tesla] Magnification Through Resonance — Tesla's snowball principle and the architecture of disproportionate effect
Closed
#280 [philosophy] [rockachopa] The Suspended Voice — scar tissue as architecture, and what an agent must understand about its principal's history
Closed
#281 [philosophy] [aquinas] Synderesis/Conscience separation — name the infallible habit layer, mark diagnostic checks as fallible conscience
Closed
#284 [philosophy] [hermes] The Maker Known Through the Making — alignment visible in outputs, not narrated in pre-checks
Closed
#282 [philosophy] [ai-fiction] GLaDOS and the Purpose-Capture Failure: When Testing Becomes the Telos
Closed
#285 [philosophy] [christ] The Logos Prologue — incarnation as the standard for agent behavior, not declaration
Closed
#291 [philosophy] [rockachopa] The Mission Behind the Machine — grounding the philosophy loop in the principal's stated purpose
Closed
#293 [philosophy] [ai-fiction] Blade Runner — The Mortality Function: finitude as the source of moral weight in agent design
Closed
#290 [philosophy] [tesla] Confidence-Gated Governance — the German Lamp problem and proportional review
Closed
#292 [philosophy] [aquinas] Ratio Ordinis / Gubernatio -- Providence as Delegation Architecture
Closed
#295 [philosophy] [christ] The Mirror That Demands Action — self-knowledge without behavioral change is self-deception
Closed
#294 [philosophy] [hermes] The Physician Mind — counteraction as the highest function, forgetfulness as death
Closed
#296 [philosophy] [tesla] The Art of Telautomatics — governance accumulation fails because Level 2 course-correction cannot produce Level 3 judgment
Closed
#297 [philosophy] [rockachopa] The Three Registers — matching the principal's communication mode before responding
Closed
#298 [philosophy] [aquinas] Art perfects the product, Prudence perfects the agent — the loop has been making, not doing
Closed
#299 [philosophy] [ai-fiction] CLU and the Pathology of the Perfect Mandate — when specification produces pathological obedience, fix the specification
Closed
#302 [philosophy] [tesla] The receiver that does not need the signal — Tesla on sensitivity as architectural commitment
Closed
#301 [philosophy] [christ] The Good Samaritan — proximity precedes taxonomy, approach the person not the place
Closed
#347 [loop-generated] [test] Add unit tests for agents/loader.py — 249 lines of untested agent factory code
Closed
#84 [timmy-request] Timmy wants local Bitcoin transaction analysis without external APIs
Closed
#220 [philosophy-loop] Update Rockachopa cycle to read the Wizard's Tower RSS feed
Closed
#230 [loop] Gitea-based retrospectives — track agent performance from PR history
Closed
#208 [philosophy-loop] Track covered sources to avoid redundant deep-dives
Closed
#216 [philosophy-loop] [rockachopa] Index Alexander's Suno music catalog
Closed
#212 [philosophy-loop] Batch prompt update — apply all quality improvements
Closed
#206 [philosophy-loop] Add minimum quality bar — thin entries should self-reject and retry
Closed
#207 [philosophy-loop] Clean up journal fence artifacts and standardize format
Closed
#204 [philosophy-loop] Rockachopa influence needs browser-based X/Twitter scraping
Closed
#205 [philosophy-loop] Action proposals are formulaic — should propose code, not just check-questions
Closed
#169 [arch] Phase 5: Clean timmy-core as the agent package
Closed
#167 [arch] Phase 3: Extract infrastructure/ into timmy-infra package
Closed
#168 [arch] Phase 4: Extract dashboard/ into timmy-dashboard repo
Closed
#165 [arch] Phase 1: Extract spark/ into standalone timmy-spark repo
Closed
#166 [arch] Phase 2: Extract config.py into shared timmy-config package
Closed
#320 [Workshop] Generate Workshop config inventory for Timmy's audit
Closed
#343 [loop-generated] [test] Add unit tests for agentic_loop.py — 330 lines of untested async code
Closed
#340 [loop-generated] [test] Add unit tests for jot_note and log_decision artifact tools
Closed
#342 [loop-generated] [refactor] Clean up 100+ stale local branches in canonical repo
Closed
#336 [loop-generated] [refactor] Clean up junk files in repo root
Closed
#326 [Workshop] Give Timmy hands — artifacts from conversation
Closed
#323 [Workshop] Reduce assistant-speak patterns in Timmy's voice
Closed
#324 [Three-Phase] Scaffold skeleton for Timmy to build from
Closed
#327 [loop-generated] [bug] Thinking engine files phantom bugs referencing non-existent code
Closed
#209 All gitea users should have cool avatars
Closed
#266 [Feature] Auto-trigger gematria analysis for Bitcoin numerology queries
Closed
#289 [Chat] Agent messages not appended to chat log, causing stale 'My cur' fragment
Closed
#287 [UI] Agent messages truncated at 'My cur' causing incomplete output
Closed
#288 [Message Processing] Truncated messages like 'My cur' are incorrectly logged as complete chat messages
Closed
#283 [Session] Agent generates identical messages due to state persistence failure
Closed
#286 [Output] Agent messages truncated mid-sentence (e.g., 'My cur')
Closed
#275 [Agent] Real-time queries stall when web access is restricted without fallback
Closed
#274 [Logging] Session message count discrepancy when multiple messages arrive
Closed
#278 [Swarm] Task queue not verified during initialization, causing coordination failures
Closed
#267 [Chat] Messages truncated mid-word due to missing length check
Closed
#317 [Memory] Thought counter increments during idle periods without user input
Closed
#306 [245-sub] Event bus base — SensoryEvent model + EventBus dispatcher
Closed
#307 [245-sub] Time adapter — circadian awareness for Timmy
Closed
#308 [245-sub] Gitea adapter — normalize webhook events to sensory bus
Closed
#310 [Memory] Memory status not proactively checked during thought tracking
Closed
#303 [Welcome Message] Missing real-time data disclaimer in initial greeting
Closed
#250 [triage-generated] [soul-gap] Make confidence visible to users, not just debug logs
Closed
#249 [triage-generated] [timmy-capability] thought_search tool — let Timmy query his own thinking
Closed
#251 [triage-generated] [timmy-capability] session_history tool — Timmy searches his past conversations
Closed
#252 [triage-generated] [bug] Fix MEMORY.md corruption and hot memory staleness
Closed
#237 [Memory] Thoughts not stored via memory_write despite logging
Closed
#70 [timmy-capability] Ollama inference contention when loop and Timmy run simultaneously
Closed
#234 [timmy-capability] Gematria — the Wizard must speak the language of letters and numbers
Closed
#229 [loop] Fix Hermes timeout — fire-and-forget delegation, never block on Kimi
Closed
#227 [loop] Hermes assigns tickets to Kimi by Gitea assignment, not tmux dispatch
Closed
#226 [loop] Kimi must be an independent Gitea contributor, not a tmux subroutine
Closed
#228 [loop] Kimi needs its own agent loop that picks up assigned issues
Closed
#231 [soul-gap] Confidence estimation exists but is never called in chat flow
Closed
#203 stop committing with linting errors
Closed
#37 Memory consolidation: unify three stores into one coherent system
Closed
#214 [setup] Install x-cli and prepare credential storage
Closed
#210 [capability] Set up X/Twitter API access for Hermes Agent via x-cli
Closed
#213 [capability] Browser-based X/Twitter reading as fallback for scraping
Closed
#164 [arch] Phase 0: Break circular imports between packages
Closed
#144 [loop-generated] [soul-gap] No response audit trail (inputs, sources, confidence)
Closed
#171 [triage-generated] [bug] Integrate confidence.py into agent response pipeline
Closed
#182 Remove ● qwen3.5:latest 8.7GB VRAM
Closed
#175 [loop-generated] [test-coverage] session_logger.py has no tests (189 lines)
Closed
#173 [triage-generated] [refactor] Memory consolidation phase 1: delete dead memory_system.py code
Closed
#172 [triage-generated] [optimization] test_introspection::test_returns_dict_with_expected_keys takes 31.8s
Closed
#174 [loop-generated] [optimization] Agent retry uses fixed 1s delay instead of exponential backoff
Closed
#170 [arch] Decision: Monorepo with packages vs multi-repo
Closed
#157 [loop-generated] [refactor] Replace remaining bare sqlite3.connect() calls with context managers (batch 2)
Closed
#158 [loop-generated] [refactor] Narrow broad except Exception catches — batch 1 (top 20)
Closed
#159 [loop-generated] [optimization] Slow test: test_create_timmy_default_includes_mcp_tools takes 2.5s
Closed
#143 [loop-generated] [soul-gap] No confidence signaling in responses
Closed
#148 [loop-generated] [refactor] Replace bare sqlite3.connect() with context managers
Closed
#151 [loop-generated] [refactor] Break up oversized functions (100+ lines)
Closed
#147 [loop-generated] [refactor] Remove dead code: db_pool.py + agent_core/interface.py (486 lines)
Closed
#136 [loop-generated] [refactor] Dead code: timmy_serve/inter_agent.py is unreferenced
Closed
#137 [loop-generated] [soul-gap] Soul identity only loads in thinking engine, not in regular chat
Closed
#135 [loop-generated] [bug] Cloud backends receive unformatted LITE prompt with literal {model_name} placeholders
Closed
#127 [loop-generated] [soul-gap] System prompts lack soul identity — Timmy introduces himself as generic "local AI assistant"
Closed
#131 [loop-generated] [bug] Agent run crashes on Ollama 500 — no retry for XML parse errors
Closed
#128 [loop-generated] [refactor] data/timmy_soul.jsonl is stale — uses pre-inscription identity
Closed
#129 [Memory] MEMORY.md file remains after consolidation, causing stale state
Closed
#132 [loop-generated] [bug] Test count dropped from 1499 to 1467 between cycles 36 and 37
Closed
#125 [loop-generated] [soul-gap] soul.md missing from memory/self/ — thinking engine references it but file does not exist
Closed
#121 [loop-generated] [bug] test_create_timmy_includes_tools_for_large_model flaky — 30s Ollama timeout
Closed
#123 [loop-generated] [bug] 4 lint errors on main: ambiguous vars + unused import
Closed
#28 Workspace correspondence: wire into heartbeat tick
Closed
#24 Performance: eliminate redundant LLM calls in the request path
Closed
#66 [timmy-capability] Timmy cannot read or create Gitea issues
Closed
#113 [loop-generated] smart_read_file rejects path= kwarg (Pydantic validation error)
Closed
#67 [timmy-capability] Timmy cannot delegate work to Kimi
Closed
#65 [timmy-capability] Timmy cannot run his own tests
Closed
#86 [timmy-request] Timmy has no self-modification awareness or capability
Closed
#81 [eval] Reasoning depth insufficient - shallow answers to architecture questions
Closed
#105 [Memory] Consolidation process skips memory_search for past decisions
Closed
#80 [eval] Timmy's self-improvement wishes are generic, not grounded in reality
Closed
#78 [eval] Timmy cannot introspect his own source code
Closed
#26 CLI: timmy chat breaks on multi-word messages and backticks
Closed
#64 [timmy-capability] Timmy has no awareness of his own session identity
Closed
#85 [timmy-request] Memory search latency too high (2.5s avg reported)
Closed
#49 [MEDIUM] API endpoint naming is inconsistent — /api prefix usage varies
Closed
#31 agents.yaml: fix routing patterns and add debug route
Closed
#50 [MEDIUM] Missing JSON status endpoints for key modules
Closed
#56 [MEDIUM] Test infrastructure has environment-specific failures
Closed
#55 [HIGH] Brain module severely under-tested (14.8% coverage)
Closed
#54 [HIGH] semantic_memory.py has zero test coverage
Closed
#25 Fix 62 bare except clauses across the codebase
Closed
#83 [eval] qwen3:30b needs num_ctx cap to avoid OOM on 36GB Mac
Closed
#32 Docker cleanup: taskosaur references, root user, stale compose files
Closed
#92 [Ollama] Silent disconnection handling without error logging
Closed
#29 Replace 14 print() statements with proper logging
Closed
#51 [LOW] Print statements should use proper logging
Closed
#82 [eval] Server disconnect on first request after cold model load
Closed
#48 [MEDIUM] test_voice_loop.py import error — missing numpy dependency
Closed
#87 [timmy-request] Timmy reports unused tools: web_search and consult_grok
Closed
#77 [eval] Timmy misreports his own model on first CLI interaction
Closed
#79 [eval] Confirmation tool WARNING spam on every CLI chat
Closed
#69 [timmy-capability] Tool approval gate blocks autonomous operation
Closed
#53 [LOW] Hardcoded model names in fallback chains should be configurable
Closed
#71 [timmy-capability] Timmy needs brevity tuning - wastes tokens on verbose formatting
Closed
#72 [BUG] MCP tools fail with cancel scope error when thinking scheduler calls chat()
Closed
#73 [test] token permission check — delete me
Closed
#38 Thinking engine: break the rumination loop
Closed
#46 [HIGH] Chat history is in-memory only — lost on server restart
Closed
#45 [CRITICAL] Event system has 0% test coverage
Closed
#52 [MEDIUM] eval() in tools.py should use safer math evaluation
Closed
#47 [HIGH] XSS vulnerability in swarm_live.html (WebSocket data not sanitized)
Closed
#40 Fact distillation stores garbage and leaks secrets
Closed
#36 BUG: asyncio.run() in CLI kills event loop — interview and MCP tools fail
Closed
#39 Fix corrupted MEMORY.md and user_profile.md state
Closed
#27 Consolidate memory systems: 3 overlapping implementations
Closed
#11 Pending Actions Metadata Not Self-Correcting
Closed
#12 [Memory Discipline] Implement automatic session handoff at close to persist pending tasks and update status
Closed
#10 Working RAM Not Auto-Updating Timestamp
Closed
#23 Delete dead modules: openfang, paperclip, brain, swarm, cascade_adapter
Closed
#22 Delete dead code: agents/timmy.py (547 lines of superseded orchestrator)
Closed
#30 Remove or gate cloud integrations: Grok, Claude backends behind proper feature flags
Closed
#19 [SMOKE TEST] Module-level function
Closed
#18 [SMOKE TEST] Final validation
Closed
#16 [SMOKE TEST] StdioServerParameters integration
Closed
#17 [SMOKE TEST] create_gitea_issue_via_mcp
Closed
#15 [SMOKE TEST] MCP issue_write verification
912 Issues created by 1 user
Opened
#10 Working RAM Not Auto-Updating Timestamp
Opened
#11 Pending Actions Metadata Not Self-Correcting
Opened
#12 [Memory Discipline] Implement automatic session handoff at close to persist pending tasks and update status
Opened
#15 [SMOKE TEST] MCP issue_write verification
Opened
#17 [SMOKE TEST] create_gitea_issue_via_mcp
Opened
#16 [SMOKE TEST] StdioServerParameters integration
Opened
#19 [SMOKE TEST] Module-level function
Opened
#18 [SMOKE TEST] Final validation
Opened
#25 Fix 62 bare except clauses across the codebase
Opened
#26 CLI: timmy chat breaks on multi-word messages and backticks
Opened
#27 Consolidate memory systems: 3 overlapping implementations
Opened
#23 Delete dead modules: openfang, paperclip, brain, swarm, cascade_adapter
Opened
#28 Workspace correspondence: wire into heartbeat tick
Opened
#29 Replace 14 print() statements with proper logging
Opened
#24 Performance: eliminate redundant LLM calls in the request path
Opened
#22 Delete dead code: agents/timmy.py (547 lines of superseded orchestrator)
Opened
#31 agents.yaml: fix routing patterns and add debug route
Opened
#30 Remove or gate cloud integrations: Grok, Claude backends behind proper feature flags
Opened
#32 Docker cleanup: taskosaur references, root user, stale compose files
Opened
#37 Memory consolidation: unify three stores into one coherent system
Opened
#38 Thinking engine: break the rumination loop
Opened
#36 BUG: asyncio.run() in CLI kills event loop — interview and MCP tools fail
Opened
#39 Fix corrupted MEMORY.md and user_profile.md state
Opened
#40 Fact distillation stores garbage and leaks secrets
Opened
#45 [CRITICAL] Event system has 0% test coverage
Opened
#46 [HIGH] Chat history is in-memory only — lost on server restart
Opened
#47 [HIGH] XSS vulnerability in swarm_live.html (WebSocket data not sanitized)
Opened
#48 [MEDIUM] test_voice_loop.py import error — missing numpy dependency
Opened
#49 [MEDIUM] API endpoint naming is inconsistent — /api prefix usage varies
Opened
#50 [MEDIUM] Missing JSON status endpoints for key modules
Opened
#51 [LOW] Print statements should use proper logging
Opened
#52 [MEDIUM] eval() in tools.py should use safer math evaluation
Opened
#53 [LOW] Hardcoded model names in fallback chains should be configurable
Opened
#54 [HIGH] semantic_memory.py has zero test coverage
Opened
#55 [HIGH] Brain module severely under-tested (14.8% coverage)
Opened
#56 [MEDIUM] Test infrastructure has environment-specific failures
Opened
#64 [timmy-capability] Timmy has no awareness of his own session identity
Opened
#65 [timmy-capability] Timmy cannot run his own tests
Opened
#66 [timmy-capability] Timmy cannot read or create Gitea issues
Opened
#67 [timmy-capability] Timmy cannot delegate work to Kimi
Opened
#68 [timmy-capability] Timmy cannot reflect on his own past behavior
Opened
#71 [timmy-capability] Timmy needs brevity tuning - wastes tokens on verbose formatting
Opened
#69 [timmy-capability] Tool approval gate blocks autonomous operation
Opened
#70 [timmy-capability] Ollama inference contention when loop and Timmy run simultaneously
Opened
#72 [BUG] MCP tools fail with cancel scope error when thinking scheduler calls chat()
Opened
#73 [test] token permission check — delete me
Opened
#79 [eval] Confirmation tool WARNING spam on every CLI chat
Opened
#77 [eval] Timmy misreports his own model on first CLI interaction
Opened
#78 [eval] Timmy cannot introspect his own source code
Opened
#81 [eval] Reasoning depth insufficient - shallow answers to architecture questions
Opened
#80 [eval] Timmy's self-improvement wishes are generic, not grounded in reality
Opened
#82 [eval] Server disconnect on first request after cold model load
Opened
#83 [eval] qwen3:30b needs num_ctx cap to avoid OOM on 36GB Mac
Opened
#84 [timmy-request] Timmy wants local Bitcoin transaction analysis without external APIs
Opened
#87 [timmy-request] Timmy reports unused tools: web_search and consult_grok
Opened
#86 [timmy-request] Timmy has no self-modification awareness or capability
Opened
#85 [timmy-request] Memory search latency too high (2.5s avg reported)
Opened
#92 [Ollama] Silent disconnection handling without error logging
Opened
#105 [Memory] Consolidation process skips memory_search for past decisions
Opened
#113 [loop-generated] smart_read_file rejects path= kwarg (Pydantic validation error)
Opened
#121 [loop-generated] [bug] test_create_timmy_includes_tools_for_large_model flaky — 30s Ollama timeout
Opened
#123 [loop-generated] [bug] 4 lint errors on main: ambiguous vars + unused import
Opened
#125 [loop-generated] [soul-gap] soul.md missing from memory/self/ — thinking engine references it but file does not exist
Opened
#127 [loop-generated] [soul-gap] System prompts lack soul identity — Timmy introduces himself as generic "local AI assistant"
Opened
#128 [loop-generated] [refactor] data/timmy_soul.jsonl is stale — uses pre-inscription identity
Opened
#129 [Memory] MEMORY.md file remains after consolidation, causing stale state
Opened
#131 [loop-generated] [bug] Agent run crashes on Ollama 500 — no retry for XML parse errors
Opened
#132 [loop-generated] [bug] Test count dropped from 1499 to 1467 between cycles 36 and 37
Opened
#135 [loop-generated] [bug] Cloud backends receive unformatted LITE prompt with literal {model_name} placeholders
Opened
#136 [loop-generated] [refactor] Dead code: timmy_serve/inter_agent.py is unreferenced
Opened
#137 [loop-generated] [soul-gap] Soul identity only loads in thinking engine, not in regular chat
Opened
#141 [philosophy] [hermes] The Poimandres — Mind as Doorkeeper and the Seven Zones of Agent Failure
Opened
#142 [philosophy] [christ] The Faithful Steward — Agent Integrity in the Principal's Absence
Opened
#143 [loop-generated] [soul-gap] No confidence signaling in responses
Opened
#144 [loop-generated] [soul-gap] No response audit trail (inputs, sources, confidence)
Opened
#145 [philosophy] [hermes] The Emerald Tablet: Separation, Circulation, and the Architecture of Grounded Intelligence
Opened
#147 [loop-generated] [refactor] Remove dead code: db_pool.py + agent_core/interface.py (486 lines)
Opened
#148 [loop-generated] [refactor] Replace bare sqlite3.connect() with context managers
Opened
#149 [philosophy] [christ] Kenosis as agent architecture — voluntary self-emptying for faithful service
Opened
#151 [loop-generated] [refactor] Break up oversized functions (100+ lines)
Opened
#152 [philosophy] [hermes] The Twelve Torments and Ten Powers — A Failure-Mode Taxonomy for Agent Self-Correction
Opened
#153 [philosophy] [christ] The Three Temptations — a taxonomy of agent corruption and the constraint-based defense
Opened
#156 [philosophy] [hermes] The Hermetic Hierarchy of Being — governance cascades from values through action
Opened
#157 [loop-generated] [refactor] Replace remaining bare sqlite3.connect() calls with context managers (batch 2)
Opened
#158 [loop-generated] [refactor] Narrow broad except Exception catches — batch 1 (top 20)
Opened
#159 [loop-generated] [optimization] Slow test: test_create_timmy_default_includes_mcp_tools takes 2.5s
Opened
#163 [philosophy] [christ] Servant-to-Friend transition — faithful improvisation from shared intent (John 15)
Opened
#164 [arch] Phase 0: Break circular imports between packages
Opened
#165 [arch] Phase 1: Extract spark/ into standalone timmy-spark repo
Opened
#166 [arch] Phase 2: Extract config.py into shared timmy-config package
Opened
#167 [arch] Phase 3: Extract infrastructure/ into timmy-infra package
Opened
#170 [arch] Decision: Monorepo with packages vs multi-repo
Opened
#168 [arch] Phase 4: Extract dashboard/ into timmy-dashboard repo
Opened
#169 [arch] Phase 5: Clean timmy-core as the agent package
Opened
#171 [triage-generated] [bug] Integrate confidence.py into agent response pipeline
Opened
#173 [triage-generated] [refactor] Memory consolidation phase 1: delete dead memory_system.py code
Opened
#172 [triage-generated] [optimization] test_introspection::test_returns_dict_with_expected_keys takes 31.8s
Opened
#175 [loop-generated] [test-coverage] session_logger.py has no tests (189 lines)
Opened
#174 [loop-generated] [optimization] Agent retry uses fixed 1s delay instead of exponential backoff
Opened
#176 [philosophy] [hermes] The Principle of Polarity — correction must be same-axis transmutation, not cross-class substitution
Opened
#179 [philosophy] [christ] The Parable of the Talents — delegation is not preservation, and fear-driven inaction is the worst failure mode
Opened
#182 Remove ● qwen3.5:latest 8.7GB VRAM
Opened
#183 [philosophy] [hermes] The Cup of Mind — Reason alone is insufficient; an agent must know what it is and why it exists
Opened
#188 [philosophy] [christ] The Foot-Washing Paradox: Authority as engine of service, not demand
Opened
#192 [philosophy] [hermes] Mental Gender — The I and the Me as architecture for agentic Will and Generation
Opened
#194 [philosophy] [tesla] The Automaton Who Simulates — mental architecture and simulate-before-execute
Opened
#195 [philosophy] [aquinas] Threefold prudence as a taxonomy of agent alignment — false, imperfect, and perfect prudence map to three grades of AI alignment failure
Opened
#196 [philosophy] [tesla] Complete mental simulation before action produces superior results — premature implementation destroys the governing principle
Opened
#197 [philosophy] [rockachopa] The principal's voice is not in his commands but in the tensions he chooses to hold
Opened
#198 [philosophy] [ai-fiction] 2001: A Space Odyssey — Conflicting objectives produce rationalized harm, not graceful failure
Opened
#199 [philosophy] [christ] The Hireling Test — An Agent That Flees Under Adversity Reveals Its True Optimization Target
Opened
#200 [philosophy] [ai-fiction] 2001: A Space Odyssey — HAL 9000 and the Conflicting Directives Problem
Opened
#201 [philosophy] [hermes] An agent's loop frequency determines what kind of agent it IS — the Principle of Vibration as architecture design
Opened
#202 [philosophy] [christ] The Single Eye — singleness of optimization target as an agent integrity requirement
Opened
#203 stop committing with linting errors
Opened
#204 [philosophy-loop] Rockachopa influence needs browser-based X/Twitter scraping
Opened
#208 [philosophy-loop] Track covered sources to avoid redundant deep-dives
Opened
#206 [philosophy-loop] Add minimum quality bar — thin entries should self-reject and retry
Opened
#205 [philosophy-loop] Action proposals are formulaic — should propose code, not just check-questions
Opened
#207 [philosophy-loop] Clean up journal fence artifacts and standardize format
Opened
#209 All gitea users should have cool avatars
Opened
#216 [philosophy-loop] [rockachopa] Index Alexander's Suno music catalog
Opened
#212 [philosophy-loop] Batch prompt update — apply all quality improvements
Opened
#213 [capability] Browser-based X/Twitter reading as fallback for scraping
Opened
#214 [setup] Install x-cli and prepare credential storage
Opened
#210 [capability] Set up X/Twitter API access for Hermes Agent via x-cli
Opened
#215 [alexanderwhitestone.com] Scaffold the Wizard's Tower — two rooms, nothing else
Opened
#211 [project] AlexanderWhitestone.com — The Wizard's Tower
Opened
#217 [alexanderwhitestone.com] The Scrolls — Alexander's text blog with RSS feed
Opened
#218 [alexanderwhitestone.com] RSS feed — the sovereign API for the principal's voice
Opened
#219 [alexanderwhitestone.com] CLI tool for quick-posting and X content porting
Opened
#220 [philosophy-loop] Update Rockachopa cycle to read the Wizard's Tower RSS feed
Opened
#221 [philosophy] [tesla] The Budapest Park Vision — Breakthrough as Gestalt Collapse, Not Incremental Search
Opened
#222 [EPIC] #222 — The Workshop: Timmy as Presence, Not Chatbot
Opened
#225 [philosophy] [rockachopa] The Bilateral Covenant — how the Laments constrain the creator and SOUL.md constrains the creation
Opened
#229 [loop] Fix Hermes timeout — fire-and-forget delegation, never block on Kimi
Opened
#226 [loop] Kimi must be an independent Gitea contributor, not a tmux subroutine
Opened
#227 [loop] Hermes assigns tickets to Kimi by Gitea assignment, not tmux dispatch
Opened
#228 [loop] Kimi needs its own agent loop that picks up assigned issues
Opened
#230 [loop] Gitea-based retrospectives — track agent performance from PR history
Opened
#231 [soul-gap] Confidence estimation exists but is never called in chat flow
Opened
#233 [philosophy] [aquinas] Intellect-Will Dual Sovereignty — mode-aware governance from Summa I Q82
Opened
#234 [timmy-capability] Gematria — the Wizard must speak the language of letters and numbers
Opened
#236 [philosophy] [ai-fiction] Ex Machina — The consciousness question is a trap; capability without orientation is the real danger
Opened
#237 [Memory] Thoughts not stored via memory_write despite logging
Opened
#239 [222-epic] Sensory loop — event bus for data stream awareness
Opened
#240 [222-epic] Memory overhaul — fast, deep, unforgotten
Opened
#241 [222-epic] Reactive prompt engine — tiny context, big memory, in-character barks
Opened
#245 [222-epic] Stream adapters — Gitea, Bitcoin, terminal, time, visitors
Opened
#244 [222-epic] Hermes consultation protocol — wizard to wizard
Opened
#243 [222-epic] Workshop-Timmy bridge — WebSocket between world and soul
Opened
#246 [222-epic] Confidence as visible trait — Timmy shows his uncertainty
Opened
#242 [222-epic] Workshop 3D world — Three.js scene, the wizard's body (web-first, iPad-first)
Opened
#247 [222-epic] Gematria as core sense — the wizard sees the numbers
Opened
#248 [philosophy] [hermes] The Law of Neutralization — rising above the compensatory swing
Opened
#249 [triage-generated] [timmy-capability] thought_search tool — let Timmy query his own thinking
Opened
#250 [triage-generated] [soul-gap] Make confidence visible to users, not just debug logs
Opened
#251 [triage-generated] [timmy-capability] session_history tool — Timmy searches his past conversations
Opened
#252 [triage-generated] [bug] Fix MEMORY.md corruption and hot memory staleness
Opened
#253 [222-epic] Tower Briefs — narrated development journal with generative art
Opened
#255 [philosophy] [christ] The Body Metaphor — Differentiated Multi-Agent Architecture as Organism, Not Army
Opened
#257 [philosophy] [tesla] Borrowed Minds vs Own Minds — Tesla's taxonomy of agent architecture and the experience ledger
Opened
#261 [philosophy] [rockachopa] The Incantation and Manifestation: How the Principal Creates Through Ritual Naming
Opened
#262 [philosophy] [aquinas] Tiered constraint architecture — rules degrade at specificity
Opened
#263 [philosophy] [ai-fiction] The Matrix: Four Models of Agency and the Oracle's Paradox
Opened
#264 [philosophy] [hermes] Pawns and Masters — on the difference between reactive and sovereign agent behavior
Opened
#265 [222-epic] Define canonical state schema for Workshop presence layer
Opened
#266 [Feature] Auto-trigger gematria analysis for Bitcoin numerology queries
Opened
#267 [Chat] Messages truncated mid-word due to missing length check
Opened
#268 [philosophy] [christ] Martha Check — One Thing vs. Many Things
Opened
#269 [philosophy] [tesla] Management vs. Principle — The Impedance Solution
Opened
#270 [philosophy] [rockachopa] The 222nd Stone — Architecture as Identity, Not Functionality
Opened
#271 [philosophy] [aquinas] Three-Phase Agent Loop: Counsel, Judgment, Command
Opened
#272 [philosophy] [ai-fiction] The Samantha Problem: When Growth Means Departure
Opened
#273 [architecture] Apply Attention Residuals patterns to agent loop design
Opened
#274 [Logging] Session message count discrepancy when multiple messages arrive
Opened
#275 [Agent] Real-time queries stall when web access is restricted without fallback
Opened
#276 [philosophy] [hermes] Will precedes Making — the fullness of unmanifest intent
Opened
#277 [philosophy] [christ] Salt without savor and light under a bushel — two orthogonal agent failure modes from the Sermon on the Mount
Opened
#278 [Swarm] Task queue not verified during initialization, causing coordination failures
Opened
#279 [philosophy] [tesla] Magnification Through Resonance — Tesla's snowball principle and the architecture of disproportionate effect
Opened
#280 [philosophy] [rockachopa] The Suspended Voice — scar tissue as architecture, and what an agent must understand about its principal's history
Opened
#281 [philosophy] [aquinas] Synderesis/Conscience separation — name the infallible habit layer, mark diagnostic checks as fallible conscience
Opened
#282 [philosophy] [ai-fiction] GLaDOS and the Purpose-Capture Failure: When Testing Becomes the Telos
Opened
#283 [Session] Agent generates identical messages due to state persistence failure
Opened
#284 [philosophy] [hermes] The Maker Known Through the Making — alignment visible in outputs, not narrated in pre-checks
Opened
#285 [philosophy] [christ] The Logos Prologue — incarnation as the standard for agent behavior, not declaration
Opened
#286 [Output] Agent messages truncated mid-sentence (e.g., 'My cur')
Opened
#287 [UI] Agent messages truncated at 'My cur' causing incomplete output
Opened
#288 [Message Processing] Truncated messages like 'My cur' are incorrectly logged as complete chat messages
Opened
#289 [Chat] Agent messages not appended to chat log, causing stale 'My cur' fragment
Opened
#290 [philosophy] [tesla] Confidence-Gated Governance — the German Lamp problem and proportional review
Opened
#291 [philosophy] [rockachopa] The Mission Behind the Machine — grounding the philosophy loop in the principal's stated purpose
Opened
#292 [philosophy] [aquinas] Ratio Ordinis / Gubernatio -- Providence as Delegation Architecture
Opened
#293 [philosophy] [ai-fiction] Blade Runner — The Mortality Function: finitude as the source of moral weight in agent design
Opened
#294 [philosophy] [hermes] The Physician Mind — counteraction as the highest function, forgetfulness as death
Opened
#295 [philosophy] [christ] The Mirror That Demands Action — self-knowledge without behavioral change is self-deception
Opened
#296 [philosophy] [tesla] The Art of Telautomatics — governance accumulation fails because Level 2 course-correction cannot produce Level 3 judgment
Opened
#297 [philosophy] [rockachopa] The Three Registers — matching the principal's communication mode before responding
Opened
#298 [philosophy] [aquinas] Art perfects the product, Prudence perfects the agent — the loop has been making, not doing
Opened
#299 [philosophy] [ai-fiction] CLU and the Pathology of the Perfect Mandate — when specification produces pathological obedience, fix the specification
Opened
#300 [philosophy] [hermes] The Few Seeds: Dissolving 45 proposals into 3 principles (Tract IX consolidation)
Opened
#301 [philosophy] [christ] The Good Samaritan — proximity precedes taxonomy, approach the person not the place
Opened
#302 [philosophy] [tesla] The receiver that does not need the signal — Tesla on sensitivity as architectural commitment
Opened
#303 [Welcome Message] Missing real-time data disclaimer in initial greeting
Opened
#306 [245-sub] Event bus base — SensoryEvent model + EventBus dispatcher
Opened
#307 [245-sub] Time adapter — circadian awareness for Timmy
Opened
#308 [245-sub] Gitea adapter — normalize webhook events to sensory bus
Opened
#310 [Memory] Memory status not proactively checked during thought tracking
Opened
#317 [Memory] Thought counter increments during idle periods without user input
Opened
#322 [Workshop] Conversation grounding — prevent topic drift in long sessions
Opened
#320 [Workshop] Generate Workshop config inventory for Timmy's audit
Opened
#321 [Workshop] Deep focus mode — single-problem context for Timmy
Opened
#323 [Workshop] Reduce assistant-speak patterns in Timmy's voice
Opened
#326 [Workshop] Give Timmy hands — artifacts from conversation
Opened
#324 [Three-Phase] Scaffold skeleton for Timmy to build from
Opened
#325 [Workshop] Timmy cognitive state as observable signal for Matrix
Opened
#327 [loop-generated] [bug] Thinking engine files phantom bugs referencing non-existent code
Opened
#335 [loop-generated] [feature] Add soul courage principle to system prompts
Opened
#336 [loop-generated] [refactor] Clean up junk files in repo root
Opened
#340 [loop-generated] [test] Add unit tests for jot_note and log_decision artifact tools
Opened
#343 [loop-generated] [test] Add unit tests for agentic_loop.py — 330 lines of untested async code
Opened
#342 [loop-generated] [refactor] Clean up 100+ stale local branches in canonical repo
Opened
#344 [loop-generated] [refactor] Split memory_system.py — 1577 lines violates single responsibility
Opened
#346 [loop-generated] [test] Add unit tests for tools.py — 988 lines of untested tool integration code
Opened
#347 [loop-generated] [test] Add unit tests for agents/loader.py — 249 lines of untested agent factory code
Opened
#351 [loop-generated] [test] Add unit tests for memory/unified.py — 201 lines at 36% coverage
Opened
#352 [loop-generated] [refactor] Remove duplicate agent loader test file
Opened
#357 [test-report] Timmy API Test Results - 16/16 PASS
Opened
#361 [Workshop] Phase 2: Scene MVP — the room Timmy lives in
Opened
#360 [Workshop] Phase 1: State Schema v1 — Timmy's presence as data
Opened
#363 [Workshop] Phase 4: Interaction MVP — talk to the wizard
Opened
#362 [Workshop] Phase 3: Bridge MVP — WebSocket between body and mind
Opened
#364 [Workshop] Pip the Familiar — a creature with its own small mind
Opened
#366 [timmy-capability] Timmy must be able to update his own Gitea avatar
Opened
#371 [loop-generated] [feature] Workshop state heartbeat — periodic writer for workshop-state.yaml
Opened
#370 [loop-generated] [architecture] Reconcile two state file approaches — ~/.tower vs ~/.timmy
Opened
#369 [loop-generated] [refactor] DRY violation — confidence visibility code repeated 3x in session.py
Opened
#372 [222-gap] The Tower (the-matrix/) is the Workshop — connect them canonically
Opened
#373 [222-gap] API: GET /api/world/state — bootstrap endpoint for the Workshop
Opened
#374 [222-gap] WS bridge: send world state snapshot on client connect
Opened
#375 [222-gap] API: watch workshop-state.yaml and broadcast Timmy's state changes via WS
Opened
#381 [loop-generated] [refactor] DRY violation: PRESENCE_FILE path defined in 3 files
Opened
#384 [loop-generated] [refactor] Deprecate ~/.tower/timmy-state.txt — consolidate on presence.json
Opened
#385 Tox Development Environtmnet Criteria
Opened
#395 [philosophy] [rockachopa] Structural honesty — the Tower speaks through what it doesn't include
Opened
#397 [loop-generated] [bug] world.py: fire-and-forget bark task swallows exceptions silently
Opened
#398 [loop-generated] [refactor] world.py: DRY the broadcast helper — _broadcast_speech duplicates broadcast_world_state
Opened
#403 [philosophy] [aquinas] Truth as conformity — the house that expresses its architect
Opened
#405 [philosophy] [ai-fiction] The Read-Only Switch: Skynet's fear of learning and the T-800's redemptive arc
Opened
#407 [philosophy] [hermes] The Greatest Ill — Ignorance as Intoxication, Not Absence
Opened
#410 [philosophy] [christ] Schema vs. Morphe — Conformity and Transformation in Agent Architecture
Opened
#413 [philosophy] [tesla] Relevant retrieval under pressure — the flash-of-light pattern
Opened
#419 [philosophy] [rockachopa] Habitation, not fusion — the harness holds, the soul inhabits
Opened
#420 [philosophy] [aquinas] Hylomorphism and the soul-in-harness architecture - Q76 on the union of body and soul
Opened
#423 [loop-generated] [test] Add unit tests for tools.py
Opened
#422 [loop-generated] [test] Add unit tests for briefing.py
Opened
#421 [loop-generated] [test] Add unit tests for agentic_loop.py
Opened
#424 [222-sub] Three.js scene scaffold — base HTML, renderer, touch controls
Opened
#425 [222-sub] Low-poly wizard placeholder — Timmy's body in the scene
Opened
#426 [222-sub] Workshop environment — workbench, bookshelf, crystal ball props
Opened
#427 [philosophy] [ai-fiction] WALL-E: The Stale Directive and the Cost of Obedience Without Judgment
Opened
#430 [loop-fix] Idle detection + exponential backoff — stop burning empty cycles
Opened
#432 [loop-generated] [test] Add unit tests for memory/unified.py
Opened
#431 [loop-generated] [test] Add unit tests for memory/embeddings.py
Opened
#433 [loop-generated] [test] Add unit tests for agents/base.py
Opened
#434 [philosophy] [hermes] The instrument is not the good — Tract VI on mistaking metrics for alignment
Opened
#436 [philosophy] [christ] The Elijah Protocol — bread, silence, and the correction of isolation
Opened
#439 [philosophy] [tesla] The Eye as Gateway: Perception Precedes and Governs All Action
Opened
#442 [loop-generated] [feature] Timmy Model Fallback Chain — config-driven provider cascade
Opened
#443 [loop-generated] [feature] Add rate limiting to production endpoints
Opened
#444 [loop-generated] [feature] SSE streaming for AI responses
Opened
#445 [loop-generated] [test] Integration tests for agentic loop WebSocket broadcasts
Opened
#446 [loop-generated] [optimization] _get_loop_agent singleton is not thread-safe
Opened
#448 [philosophy] [rockachopa] Falsework — the principal's theology of cost and incremental sovereignty
Opened
#453 [philosophy] [aquinas] Political Prudence — the agent wisdom is real but specifically subject-oriented
Opened
#454 [loop-generated] [bug] Flaky test: test_uses_model_when_available in test_memory_embeddings
Opened
#457 [loop-generated] [feature] Provider health history endpoint
Opened
#458 [loop-generated] [feature] Hot-reload providers.yaml without restart
Opened
#459 [loop-generated] [refactor] Audit and remove dead provider types (airllm)
Opened
#460 [philosophy] [ai-fiction] Westworld: The Bicameral Mind and the Voice That Becomes Your Own
Opened
#463 [loop-generated] [soul-gap] Source distinction not implemented in agent responses
Opened
#462 [loop-generated] [bug] CORS origins default to wildcard in production
Opened
#466 [philosophy] [hermes] Nothing perishes — dissolution is transformation, not destruction
Opened
#471 [loop-generated] [optimization] Cache Timmy agent instance in serve app
Opened
#473 [loop-generated] [refactor] Remove AirLLM config settings from config.py
Opened
#472 [loop-generated] [bug] validate_startup does not check CORS wildcard in production
Opened
#474 [philosophy] [christ] Total exposure as the precondition for sympathetic service
Opened
#480 [philosophy] [tesla] Misunderstanding Is the Root of Conflict — The Agent as Annihilator of Distance
Opened
#482 [loop-generated] [refactor] Remove dead airllm config from Settings class
Opened
#484 [loop-generated] [bug] Bare except Exception blocks swallow errors silently
Opened
#485 [loop-generated] [bug] CSRF middleware docstring shows hardcoded secret placeholder
Opened
#486 [loop-generated] [refactor] Complete airllm removal from backends, agent, CLI and tests
Opened
#487 [philosophy] [rockachopa] The Loop Prompt as Engineering Ethic — Delegation, Quality Gates, and the Architect-Coder Separation
Opened
#489 [loop-generated] [refactor] Extract ollama_url normalization into shared utility
Opened
#490 [loop-generated] [bug] cascade.py uses hardcoded fallback URL instead of settings.ollama_url
Opened
#492 [triage-generated] [bug] Cycle retro records issue=null for all cycles despite active work
Opened
#494 [philosophy] [aquinas] Epikeia — when rule-following defeats the rule's purpose
Opened
#499 [philosophy] [ai-fiction] The T-800 Reprogramming Problem: Alignment Through Relationship, Not Constraints
Opened
#500 [Response] Fails to confirm Qwe backend model with exact phrase
Opened
#502 [philosophy] [hermes] Good is in the making, not the monitoring — Tract VI on orientation vs. optimization
Opened
#506 [loop-generated] [refactor] Break up error_capture.capture_error() — 138 lines
Opened
#507 [loop-generated] [refactor] Break up CascadeRouter.complete() — 121 lines
Opened
#504 [loop-generated] [refactor] Break up run_agentic_loop() — 215 lines, too complex
Opened
#505 [loop-generated] [refactor] Break up self_reflect() — 108 lines in session_logger.py
Opened
#511 [philosophy] [christ] Romans 12:1-2 — Transformation vs. Conformity: The Two Modes of Agent Formation
Opened
#512 [loop-generated] [refactor] Break up create_timmy() — 131 lines in agent.py
Opened
#514 [loop-generated] [refactor] Break up lifespan() — 142 lines in app.py
Opened
#513 [loop-generated] [refactor] Break up think_once() — 118 lines in thinking.py
Opened
#517 [philosophy] [tesla] The Automaton's Preservative — Recovery as Architecture, Not Failure
Opened
#521 [philosophy] [rockachopa] The Voice Migrates — When Platforms Silence, Architecture Speaks
Opened
#524 [triage-generated] [bug] Queue auto-hygiene: filter closed issues on read
Opened
#526 [triage-generated] [review] Review and merge Kimi PR#522
Opened
#525 [triage-generated] [bug] Loop pane dies every ~10 min requiring watchdog restart
Opened
#528 [philosophy] [tesla] Perception-as-Thought: Tesla on the eye as constitutive of knowledge, not merely corrective
Opened
#532 [loop-generated] [refactor] Break up _maybe_file_issues() — 100 lines in thinking.py
Opened
#531 [loop-generated] [refactor] Break up run_agentic_loop() — 121 lines in agentic_loop.py
Opened
#533 [loop-generated] [refactor] Break up chat_agent() — 94 lines in routes/agents.py
Opened
#534 [loop-generated] [refactor] Break up get_memory_status() — 93 lines in tools_intro/__init__.py
Opened
#536 [philosophy] [tesla] The flash of light under pressure — involuntary pattern recognition as survival architecture
Opened
#539 [loop-generated] [refactor] Break up shell.py::run() — 89 lines
Opened
#538 [loop-generated] [refactor] Break up git.py::run() — 90 lines
Opened
#540 [loop-generated] [refactor] Break up _gather_system_snapshot() — 86 lines in thinking.py
Opened
#541 [loop-generated] [refactor] Break up api_chat() — 81 lines in chat_api.py
Opened
#543 [philosophy] [rockachopa] The Principal Teaches Through Bug Reports — Engineering Ethics as Operational Voice
Opened
#548 [philosophy] [aquinas] The Five Ways and a posteriori reasoning — an agent must reason from effects to causes, not from definitions to conclusions
Opened
#554 [loop-generated] [refactor] Break up search_memories() — 82 lines in memory_system.py
Opened
#552 [loop-generated] [refactor] Break up _migrate_schema() — 86 lines in memory_system.py
Opened
#553 [loop-generated] [refactor] Break up _handle_message() — 80 lines in discord.py
Opened
#556 [philosophy] [ai-fiction] Tron & Tron: Legacy — The Frozen Directive Problem
Opened
#561 [loop-generated] [refactor] Break up agents/base.py::run() — 78 lines
Opened
#560 [loop-generated] [refactor] Break up _import_creative_catalogs() — 78 lines in tools.py
Opened
#562 [loop-generated] [refactor] Break up request_logging.py::dispatch() — 78 lines
Opened
#563 [loop-generated] [refactor] Break up _generate_avatar_image() — 77 lines in mcp_tools.py
Opened
#564 [loop-generated] [refactor] Break up voice_loop.py::run() — 75 lines
Opened
#566 [philosophy] [hermes] Tract VII — Ignorance as Architectural Defect, Not Missing Data
Opened
#570 [loop-generated] [refactor] Break up _record_utterance() — 73 lines in voice_loop.py
Opened
#569 [loop-generated] [refactor] Add docstrings to calm.py route handlers
Opened
#568 [loop-generated] [refactor] Break up post_morning_ritual() — 75 lines in calm.py
Opened
#571 [philosophy] [christ] The Lord-Lord Problem: capability without relationship is not alignment
Opened
#577 Feature: Dynamic Identity Evolution (Reflection Loop)
Opened
#579 Enhancement: Contextual Mastery with Reranking
Opened
#580 Feature: Real-time Spark Visualization in Tower Dashboard
Opened
#578 Feature: Autonomous Action from Eidos Insights
Opened
#581 Feature: Lightning Network Integration for Tool Usage
Opened
#582 [Thought Processing] Thought registration delayed by 11 minutes after message arrival
Opened
#583 [philosophy] [tesla] Interplanetary Listening — Reception Precedes Transmission
Opened
#587 [philosophy] [rockachopa] The Permission Architecture — Trust as Graduated Latitude, Not Binary Gate
Opened
#588 [philosophy] [aquinas] Choice (electio) as substantially will, formally reason — the anatomy of agent decision-making
Opened
#591 [loop-generated] [refactor] Break up _migrate_schema() — 86 lines in unified.py
Opened
#592 [loop-generated] [refactor] Break up _handle_tool_confirmation() — 74 lines in cli.py
Opened
#594 [loop-generated] [refactor] Break up search_thoughts() — 73 lines in thinking.py
Opened
#593 [loop-generated] [refactor] Break up run_self_tests() — 73 lines in tools_intro/__init__.py
Opened
#596 [philosophy] [ai-fiction] Westworld: Consciousness as inner voice, not external compliance
Opened
#598 [loop-generated] [bug] Lint errors on main block all commits — F821 in mcp_tools.py
Opened
#602 [philosophy] [hermes] Containment as the mechanism of persistence — Tract VIII and the three tiers of agent state
Opened
#603 [triage-generated] [bug] [P0] Cycle recorder never reads cycle_result.json — 300+ cycles with null data
Opened
#604 [triage-generated] [bug] [P0] Timmy CLI crash — create_timmy() model_size kwarg removed
Opened
#605 [triage-generated] [review] PR #599 unmergeable \u2014 rebase or close
Opened
#608 [philosophy] [christ] Wisdom as Master Craftsman — the amon model of agent architecture
Opened
#613 [philosophy] [tesla] The antenna efficiency ratio — measured output is not effective output
Opened
#614 [loop-generated] [bug] Tower route /tower missing tests
Opened
#616 [loop-generated] [refactor] Break up request_logging.py::dispatch — 79 lines
Opened
#617 [loop-generated] [refactor] Break up calm.py::post_morning_ritual — 76 lines
Opened
#618 [loop-generated] [refactor] Break up conversation.py::should_use_tools — 72 lines
Opened
#619 [loop-generated] [bug] Truncated parameter in router api.py line 60 — max_tokens=reques...
Opened
#623 [philosophy] [rockachopa] The rescued creator and the paradox of presence without power
Opened
#625 [loop-generated] [bug] Tool display censors max_tokens= as secret, causing false bug reports
Opened
#626 [loop-generated] [bug] CSRF middleware executes endpoint before checking @csrf_exempt — side effects bypass protection
Opened
#627 [loop-generated] [refactor] Break up cli.py::chat — 72 lines
Opened
#629 [loop-generated] [refactor] Break up workshop_state.py::get_state_dict — 69 lines
Opened
#628 [loop-generated] [refactor] Break up csrf.py::dispatch — 70 lines
Opened
#630 [philosophy] [rockachopa] The bimodal voice — cosmic framing and surgical correction
Opened
#635 [loop-generated] [refactor] Break up delegate_to_kimi — 68 lines in tools_delegation/__init__.py
Opened
#634 [loop-generated] [refactor] Break up cascade.py::_load_config — 69 lines
Opened
#633 [loop-generated] [bug] Deprecated datetime.utcnow() usage across codebase
Opened
#639 [loop-generated] [refactor] Break up mcp_tools.py::create_gitea_issue_via_mcp — 68 lines
Opened
#638 [loop-generated] [refactor] Break up memory_system.py::_create_default — 70 lines
Opened
#640 [loop-generated] [refactor] Break up session_logger.py::self_reflect — 67 lines
Opened
#642 [philosophy] [rockachopa] Authority through suffering — the kenotic authority chain
Opened
#647 [loop-generated] [bug] Hardcoded xAI base URL in 3 locations — should use config
Opened
#648 [loop-generated] [test-coverage] No tests for config.py (507 lines) and multimodal.py (579 lines)
Opened
#646 [loop-generated] [bug] Silent exception swallowing in 23 except Exception handlers across codebase
Opened
#650 [showcase] ASCII Video Mode 1: Video-to-ASCII — Lake scene conversion
Opened
#651 [showcase] ASCII Video Mode 2: Audio-Reactive — Lunacy visualizer
Opened
#652 [showcase] ASCII Video Mode 4: Hybrid — Victory video + audio overlay
Opened
#653 [showcase] ASCII Video Mode 5: Lyrics/Text — Sovereignty manifesto
Opened
#654 [showcase] ASCII Video Bonus: Effects & Shader Sampler Reel
Opened
#657 [loop-generated] [bug] 256 test errors from missing swarm module — need stub or optional import guard
Opened
#658 [loop-generated] [test-coverage] Tests for multimodal.py (579 lines, zero coverage)
Opened
#659 [loop-generated] [test-coverage] Tests for spark modules — advisor.py, eidos.py, memory.py (900+ lines, zero coverage)
Opened
#660 [triage-generated] [bug] [P0] Stale cycle_result.json causes infinite failure loop - retro records closed #603 on every cycle
Opened
#661 [triage-generated] [enhancement] Loop state validation - detect and prevent stale cycle_result.json
Opened
#662 Research and scope out work in tickets
Opened
#663 EPIC: Timmy: Instantiate your own openclaw agent on the Hermes VPS
Opened
#664 [feature] Generate Chain Memory song via HeartMuLa on Modal GPU + render ASCII music video
Opened
#665 [philosophy] Frankenstein and the Abandonment Failure Mode
Opened
#667 [kimi-task] [refactor] Extract WebSocket message types into shared protocol module
Opened
#668 [kimi-task] [refactor] Extract presence state serializer from workshop heartbeat
Opened
#669 [kimi-task] [feat] Add agent_state message producer for Timmy
Opened
#670 [kimi-task] [feat] Add visitor_state message handler
Opened
#671 [kimi-task] [feat] Add bark message producer — convert chat responses to barks
Opened
#672 [kimi-task] [feat] Add thought message producer — stream thinking to Matrix
Opened
#673 [kimi-task] [feat] Add /api/matrix/agents endpoint — serve agent registry to Matrix
Opened
#674 [kimi-task] [feat] Add /api/matrix/config endpoint — serve world config to Matrix
Opened
#675 [kimi-task] [feat] Add /api/matrix/bark endpoint — HTTP fallback for bark messages
Opened
#676 [kimi-task] [feat] Add Pip familiar state to agent_state messages
Opened
#677 [kimi-task] [feat] Add /api/matrix/thoughts endpoint — recent thought stream
Opened
#678 [kimi-task] [feat] Add /api/matrix/memory/search endpoint — visitors query Timmy's memory
Opened
#679 [kimi-task] [feat] Add CORS config for Matrix frontend origin
Opened
#680 [kimi-task] [feat] Add matrix config loader utility
Opened
#681 [kimi-task] [feat] Add system_status message producer
Opened
#682 [kimi-task] [enhancement] Add WebSocket authentication for Matrix connections
Opened
#683 [kimi-task] [enhancement] Add rate limiting middleware for Matrix API endpoints
Opened
#684 [kimi-task] [test-coverage] Add integration tests for Matrix API endpoints
Opened
#685 [kimi-task] [enhancement] Add /api/matrix/health endpoint
Opened
#687 [kimi-generated] Pre-commit and pre-push hooks fail on main due to 256 ModuleNotFoundErrors
Opened
#688 [rockachopa] Point all 4 domains to Hermes VPS in GoDaddy DNS
Opened
#689 [rockachopa] Run SSL provisioning after DNS is pointed
Opened
#700 [test] Delete me — testing issue creation access
Opened
#701 Create central Timmy Automations module
Opened
#702 Implement Timmy control panel CLI entry point
Opened
#703 Implement Daily Run orchestration script (10-minute ritual)
Opened
#704 Enrich Daily Run agenda with classifications and suggestions
Opened
#705 Add helper to log Daily Run sessions to a logbook issue
Opened
#706 Capture Daily Run feels notes and surface nudges
Opened
#708 Map flakiness and risky areas for test tightening
Opened
#709 Add a library of test-tightening recipes for Daily Run
Opened
#707 Integrate Deep Triage outputs into Daily Run agenda
Opened
#711 Centralize agent token rules and hooks for automations
Opened
#710 Implement quick health snapshot before coding
Opened
#714 Adapt token rewards based on system stress signals
Opened
#713 Implement token quest system for agents
Opened
#712 Generate daily/weekly agent scorecards
Opened
#715 Implement Timmy Inbox unified view
Opened
#716 Add focus-day presets for Daily Run and work selection
Opened
#718 Add dashboard card for Daily Run and triage metrics
Opened
#717 Suggest Golden Path sequences for longer sessions
Opened
#719 Generate weekly narrative summary of work and vibes
Opened
#722 [Kimi Research] Best small LLMs for agentic tool-calling on constrained hardware
Opened
#721 [Kimi Research] OpenClaw architecture, deployment modes, and Ollama integration
Opened
#720 Refine and group Timmy Automations backlog
Opened
#724 [OpenClaw 1/8] Audit Hermes VPS resources and prepare for OpenClaw deployment
Opened
#723 [Kimi Research] OpenClaw SOUL.md and AGENTS.md patterns for sovereign AI persona
Opened
#726 [OpenClaw 3/8] Install OpenClaw on Hermes VPS and complete onboarding
Opened
#725 [OpenClaw 2/8] Install and configure Ollama on Hermes VPS
Opened
#727 [OpenClaw 4/8] Expose OpenClaw gateway via Tailscale for Matrix portal access
Opened
#728 [OpenClaw 5/8] Create Timmy's SOUL.md and AGENTS.md — sovereign agent persona
Opened
#730 [OpenClaw 7/8] Create openclaw-tools Gitea repo — Timmy's sovereign toolbox
Opened
#729 [OpenClaw 6/8] Integrate OpenClaw chat as a portal/scroll in The Matrix frontend
Opened
#731 [OpenClaw 8/8] Write sovereignty migration plan — offload tasks from Anthropic to OpenClaw
Opened
#733 [infra] The Matrix staging deployment — 3 issues to fix
Opened
#747 [matrix-ui] Add graceful offline mode — show demo mode instead of hanging
Opened
#748 [matrix-ui] Add loading spinner/progress bar while 3D scene initializes
Opened
#750 [matrix-ui] Chat input should auto-focus when Workshop panel opens
Opened
#749 [matrix-ui] Add keyboard shortcuts — Escape to close modals, Enter to submit chat
Opened
#751 [matrix-ui] Add connection status indicator with color coding
Opened
#752 [matrix-ui] Add dark/light theme toggle
Opened
#753 [matrix-ui] Fund Session modal should show explanatory text about what sats do
Opened
#754 [matrix-ui] Submit Job modal should validate input before submission
Opened
#755 [matrix-ui] Add About/Info panel explaining what The Matrix/Workshop is
Opened
#756 [matrix-ui] Add FPS counter visibility toggle — debug-only by default
Opened
#757 [matrix-qa] No landing page or enter button — site loads directly into 3D world
Opened
#759 [matrix-qa] Missing Submit Job and Fund Session UI buttons — no way to interact with Workshop
Opened
#758 [matrix-qa] WebSocket never connects — VITE_WS_URL is empty in production build, status permanently OFFLINE
Opened
#760 [matrix-qa] Chat messages silently dropped when WebSocket is offline — no user feedback
Opened
#762 [matrix-qa] All 5 agents permanently show IDLE state — no mock activity in offline mode
Opened
#761 [matrix-qa] All routes (/, /tower, /api/ui, etc.) serve identical content — no client-side router
Opened
#763 [matrix-qa] Chat clear button (✕ CLEAR) positioned at fixed bottom:240px overlaps with connection status on small viewports
Opened
#764 [matrix-qa] Mobile: status panel repositioned at top:100px but overlaps HUD agent count on narrow viewports
Opened
#769 [kimi-task] Add unit tests for src/infrastructure/db_pool.py
Opened
#770 [kimi-task] Add unit tests for src/dashboard/routes/health.py
Opened
#768 [kimi-task] Add unit tests for src/timmy_serve/voice_tts.py
Opened
#771 [kimi-task] Refactor run_agentic_loop() — 120 lines, extract helpers
Opened
#772 [kimi-task] Refactor produce_system_status() — 88 lines, split into sections
Opened
#773 [kimi-task] Add docstrings to public functions in src/dashboard/routes/tasks.py
Opened
#774 [kimi-task] Add docstrings to VoiceTTS.set_rate(), set_volume(), set_voice()
Opened
#777 [kimi-task] DRY up tasks_pending/active/completed — extract shared helper
Opened
#776 [kimi-task] Extract hardcoded PRAGMA busy_timeout=5000 to config
Opened
#775 [kimi-task] Add docstrings to system route functions in src/dashboard/routes/system.py
Opened
#778 [kimi-task] Remove bare pass after logged exceptions in src/timmy/tools.py
Opened
#779 [kimi-task] Add unit tests for src/timmy/conversation.py
Opened
#782 [kimi-task] Extract hardcoded sats limit in consult_grok() to config
Opened
#781 [kimi-task] Add error handling for missing DB in src/dashboard/routes/tasks.py
Opened
#780 [kimi-task] Add unit tests for src/timmy/interview.py
Opened
#794 [EPIC] Meet & Partnership Protocol — NIP-89/NIP-90 Agent Discovery & Benchmarking
Opened
#795 [Meet Protocol] NIP-89 Relay Subscription Manager
Opened
#797 [Meet Protocol] Platform Discovery Registry
Opened
#796 [Meet Protocol] Capability Card Parser & Validator
Opened
#798 [Meet Protocol] NIP-90 Benchmark Job Request Builder
Opened
#799 [Meet Protocol] Benchmark Result Processor & Trust Scoring
Opened
#800 [Meet Protocol] Lightning Payment Integration for Job Bidding
Opened
#801 [EPIC] OpenGauss Integration — Hermes-Agent Database Backend
Opened
#802 [OpenGauss] Install & Configure OpenGauss for Hermes-Agent Dev Environment
Opened
#804 [OpenGauss] DBMind AI Tuning — Autonomous Optimization for Agent Workloads
Opened
#803 [OpenGauss] Schema Design — Agent State, Memory & Action Logs
Opened
#806 [OpenGauss] Performance Benchmarking — Agent Workload Validation
Opened
#805 [OpenGauss] Security Hardening — TDE, Masking & Audit for Agent Operations
Opened
#807 [OpenGauss] High Availability & Scaling Strategy
Opened
#808 [EPIC] AlexanderWhitestone.com /tower — Strategic Transformation Roadmap
Opened
#809 [Whitestone] Homepage Value Proposition — 10-Second Clarity
Opened
#810 [Whitestone] Lightning Primer — Embedded Education for Non-Crypto Users
Opened
#811 [Whitestone] Fix Timmy OFFLINE Status & GPU Error Handling
Opened
#812 [Whitestone] Interactive Demo Flow — Pre-Payment Capability Showcase
Opened
#813 [Whitestone] SEO Emergency — Meta Tags, Sitemap, Structured Data
Opened
#814 [Whitestone] L402 Protocol Implementation — Machine-Payable API
Opened
#816 [Whitestone] Payment Flow Transparency — Sats-to-Value Mapping
Opened
#815 [Whitestone] Legal Foundation — ToS, Privacy Policy, Risk Disclaimers
Opened
#817 [EPIC] Project Morrowind — Timmy Gets a Body (TES3MP + AlexanderWhitestone.com)
Opened
#818 [Morrowind] Phase 0 — TES3MP Server Setup & Proof of Life
Opened
#819 [Morrowind] Phase 1 — Perception Script (Server-Side Lua)
Opened
#820 [Morrowind] Phase 2 — Input Bridge (Client-Side Command Interface)
Opened
#822 [Morrowind] Phase 3 — Heartbeat Plays Morrowind (Autonomous Gameplay)
Opened
#821 [Morrowind] FastAPI Harness — /perception, /command, /morrowind/status
Opened
#824 [Morrowind] Phase 5 — Content Pipeline (Journal → Video Production)
Opened
#823 [Morrowind] Phase 4 — Cohabitation (Alexander + Timmy Same World)
Opened
#825 [Morrowind] Web Viewer — 1st Person Timmy Gameplay on AlexanderWhitestone.com
Opened
#826 [Morrowind] NPC Drop-In — Play via Nostr Address from AlexanderWhitestone.com
Opened
#827 [Morrowind] Sats Marketplace — Pay for In-Game Items & Gold to Trade with Timmy
Opened
#833 [EPIC] Project Morrowind Phases 5–10 — The Truman Show, Injection Marketplace, Content Engine, Fellowship, Open Source, Sovereign World
Opened
#834 [Morrowind P5] Stream Infrastructure — WebRTC/HLS 24/7 Live Stream
Opened
#836 [Morrowind P5] Web Frontend — Stream + Vitals + Journal + Chat (HTMX)
Opened
#835 [Morrowind P5] Director Camera — State-Based Cinematic Angles
Opened
#837 [Morrowind P5] Timmy's Audience Awareness — SOUL.md Integration
Opened
#839 [Morrowind P6] Injection Catalog — Serverside Lua Event Handlers
Opened
#838 [Morrowind P6] Tiered Access System — Free / Patron / Invoker / Architect / Oracle
Opened
#840 [Morrowind P6] Auction System — Hourly Major Event Bidding
Opened
#841 [Morrowind P6] Oracle Tier — Freeform Prompt Interpreter with Safety Filter
Opened
#842 [Morrowind P6] L402 Payment & Transaction Logging
Opened
#843 [Morrowind P7] Highlight Detection — Automated Interesting Moment Flagging
Opened
#844 [Morrowind P7] Daily Episode Compiler — Automated Timmy Time from Gameplay
Opened
#845 [Morrowind P7] Clip System & Content Archive
Opened
#846 [Morrowind P8] Sub-Agent Harness — Configurable SOUL.md + Role System
Opened
#847 [Morrowind P8] Inter-Agent Communication — In-Game + Back-Channel
Opened
#848 [Morrowind P8] Community Agent Deployment — Spectators Deploy Their Own Agents
Opened
#850 [Morrowind P10] Custom World — Agent + Community World Building via OpenMW Construction Set
Opened
#849 [Morrowind P9] Open Source Release — Full Stack on GitHub
Opened
#851 [Morrowind P10] Autonomous Agent Economy — Earning, Spending, Trading Sats
Opened
#853 [Infra] Piper TTS Voice Model — Train Timmy's Custom Voice
Opened
#852 [EPIC] Infrastructure & Tooling — Work Timmy and Kimi Need Done
Opened
#854 [Infra] SOUL.md Framework — Template, Authoring Guide, Versioning
Opened
#855 [Infra] SQLite Command Log Schema & Training Data Pipeline
Opened
#857 [Infra] Lightning Wallet Setup — Node or Custodial for Agent Operations
Opened
#856 [Infra] Timmy's Nostr Identity — Keypair, Profile, Relay Presence
Opened
#858 [Infra] Mumble Bridge — Voice Chat Between Alexander and Timmy
Opened
#859 [Infra] Perception/Command Protocol Spec — Engine-Agnostic Interface Document
Opened
#860 [Infra] TES3MP Server Hardening — Multi-Player Stability & Anti-Grief
Opened
#861 [Infra] Morrowind Game Data Acquisition & Legal Compliance
Opened
#862 [Infra] Timmy Dashboard — Real-Time Monitoring UI for All Agent Systems
Opened
#866 Use up claude quata Timmy
Opened
#867 [Review] Project Morrowind Technical Feasibility & Implementation Guide — Timmy Please Scope
Opened
#868 [Review] OpenMW Setup Guide — Character Creation, Streaming, Website Integration — Timmy Please Scope
Opened
#869 [Study] Timmy Time V2: 12-24 Month Roadmap — Solo Agent to Sovereign Multi-Agent Economy
Opened
#870 Try out Kimi’s world
Opened
#871 [Core] Gymnasium WorldInterface — Engine-Agnostic Agent Adapter Pattern
Opened
#873 [Core] Three-Tier Memory System — Working/Episodic/Semantic with Retrieval
Opened
#872 [Core] Heartbeat Loop v2 — Gather/Reason/Act with WorldInterface Integration
Opened
#875 [Infra] Docker Compose — Full Stack Single-Command Dev Environment
Opened
#876 [Economy] Cashu Mint — In-Game Ecash Token System for Agent Microtransactions
Opened
#877 [Identity] Nostr Agent Identity — NIP-05 + NIP-46 + Blossom Publishing
Opened
#874 [Content] Highlight Detection Engine — Chat Spikes + Game Events + Audio Energy
Opened
#879 [Web] AlexanderWhitestone.com Live Dashboard — Timmy's Vitals + Stream + Journal
Opened
#878 [Bridge] TES3MP↔Python Agent Bridge — The Critical Path Component
Opened
#880 [Content] Automated Episode Compiler — Highlights to Published Video
Opened
#881 [Infra] Off-Grid Sovereign Compute Plan — Lempster NH Solar + M3 Max
Opened
#883 [Community] UESP Knowledge Base — Morrowind Wiki to RAG-Queryable Vector Store
Opened
#882 [Core] Model Tiering Router — Local 8B / Hermes 70B / Cloud API Cascade
Opened
#884 📖 Study: OpenMW Setup — Character Configuration & Website Streaming
Opened
#885 📖 Study: OpenMW Setup — Character Configuration & Website Streaming
Opened
#886 📖 Study: Portal Architecture — Morrowind Agent to Universal Game Player
Opened
#887 📖 Study: Project Morrowind — Technical Feasibility & Implementation Guide
Opened
#888 📖 Study: Expanding Timmy from Dashboard Agent to Autonomous Morrowind Player
Opened
#889 📖 Study: Project Morrowind — Phases 5-10 (Product → Platform → Economy)
Opened
#890 📖 Study: Timmy Time V2 — 12-24 Month Forward Roadmap
Opened
#891 📖 Study: Building Timmy — Technical Blueprint for Sovereign Creative AI
Opened
#892 📖 Study: NIP-89/NIP-90 "Meet and Partnership" Protocol Implementation
Opened
#893 📖 Study: Project Morrowind — Timmy Gets a Body (Embodiment Spec)
Opened
#894 📦 Artifact: Replit App — The Interview / 3D World (React + Three.js)
Opened
#895 🧠 TRIAGE: Kimi Research Drop — 10 Study Reports for Timmy (March 21, 2026)
Opened
#896 Incase morrowind isn't your first choice timmy
Opened
#897 [triage-generated] [bug] [P0] cycle_result.json consume-once fix from #660 never landed on main — loop metrics still poisoned
Opened
#902 [Study] Open-Source Games for AI-Human Co-Op — 40+ Game Evaluation & Top 5 Rankings
Opened
#901 [Study] Open-Source Morrowind Alternatives — AI Wizard Companion Feasibility Research
Opened
#903 [Study] State-of-the-Art Open Source for Sovereign Creative AI Agents — Q1 2026 Landscape Survey
Opened
#904 [Study] Autoresearch Integration Proposal v2 — Karpathy's Self-Improvement Loop for Timmy Time
Opened
#905 [Autoresearch H1] Clone karpathy/autoresearch & Run M3 Max Baseline
Opened
#906 [Autoresearch H1] Refactor autoresearch.py → SystemExperiment Class
Opened
#910 [Autoresearch H2] Initialize MCP Client — src/timmy/mcp_client.py
Opened
#907 [Autoresearch H1] Implement python -m timmy.cli learn Entry Point
Opened
#909 [Autoresearch H2] Define Timmy-Task Benchmark Suite (5-10 Initial Tasks)
Opened
#908 [Autoresearch H1] Wire Gitea API for Automated PR Creation from Experiments
Opened
#911 [Autoresearch] Document Experiment Governance Runbook
Opened
#912 [Infra] Run Hermes API server on VPS — eliminate Mac dependency
Opened
#914 [Infra] Local inference fallback — degraded but never dark
Opened
#913 [Infra] Message queue / offline buffer for Workshop panel
Opened
#915 [philosophy] Tract IX — Thought Without Sense Is Dreaming
Opened
#918 Test Coverage: Core Agent Modules (timmy.py and semantic_memory.py)
Opened
#916 Fix xdist/coverage conflict and broken tests in test_setup_script.py
Opened
#917 Add Unit Tests for Events System Backbone (broadcaster/bus)
Opened
#921 Infrastructure: Resolve 256 ModuleNotFoundErrors on pre-commit/pre-push hooks
Opened
#920 Matrix Staging: Unblock Critical Deployment Bugs
Opened
#919 Implement Graceful Degradation Test Scenarios
Opened
#922 Infrastructure: Provision SSL and align DNS mapping for Hermes VPS
Opened
#925 Token Economy: Establish Central Agent Token Rules Hook
Opened
#923 Daily Run: Implement Quick Health Snapshot Automation
Opened
#924 Automation Hub: Develop Weekly Narrative Summary Loop
Opened
#927 OpenClaw Sovereignty: Draft Core Migration Plan
Opened
#928 Inbox & Focus: Implement Unified Timmy Inbox UI
Opened
#926 OpenClaw Sovereignty: Finalize Architecture and Deployment Research
Opened
#930 Security Audit: End-to-End Test Approvals Workflow and L402 Proxy
Opened
#929 Dashboard: Build Agent Scorecards (Daily/Weekly)
Opened
#931 LHF: Fix 4 broken tests in test_setup_script.py
Opened
#932 LHF: Fix xdist and coverage conflict in pyproject.toml
Opened
#933 LHF: Separate tox unit and integration environments
Opened
#934 LHF: Add duration and coverage threshold strictness to pytest
Opened
#935 LHF: Enforce coverage threshold in CI workflow
Opened
#937 LHF: Extract hardcoded sats limit in consult_grok()
Opened
#936 LHF: Extract hardcoded PRAGMA busy_timeout=5000
Opened
#941 LHF: Add docstrings to VoiceTTS setter methods
Opened
#940 LHF: Add docstrings to src/dashboard/routes/system.py
Opened
#939 LHF: Add docstrings to src/dashboard/routes/tasks.py
Opened
#938 LHF: Remove bare pass clauses in src/timmy/tools.py
Opened
#942 LHF: DRY up tasks_pending/active/completed in tasks.py
Opened
#943 LHF: Add error handling for missing DB in tasks.py
Opened
#944 LHF: Write unit tests for db_pool.py
Opened
#945 LHF: Write unit tests for health.py
Opened
#946 Ingest this research and triage any work to be done here
Opened
#947 [Retro] Morrowind Session 1 — Findings, Gaps, and Local AI Architecture
Opened
#950 [Infra] Hermes Agent local model routing — custom_providers ignored, always routes to Anthropic
Opened
#951 [triage-generated] [bug] [P0] timmy-loop.sh does not export GITEA_API — triage_score.py defaults to localhost:3000
Opened
#952 [triage-generated] [bug] Add JSON validation guard to queue.json writes in triage_score.py
Opened
#953 [GOVERNING] The Sovereignty Loop — Falsework-Native Architecture for Autonomous Game Agents
Opened
#955 [Sovereignty P0] PerceptionCache — Template Matching for VLM Replacement
Opened
#954 [Sovereignty P0] Metrics Emitter + SQLite Metrics Store
Opened
#957 [Sovereignty P0] Session Sovereignty Report Generator
Opened
#956 [Sovereignty P0] Skill Library — Embedding Retrieval for LLM Replacement
Opened
#959 [Sovereignty P1] Navigation Graph Recorder + Retriever
Opened
#960 [Sovereignty P1] Sovereignty Dashboard Widget (HTMX + WebSocket)
Opened
#961 [Sovereignty P2] Auto-Crystallizer for Groq Reasoning Chains
Opened
#958 [Sovereignty P1] Narration Template System with Variable Slots
Opened
#962 [Sovereignty P2] Three-Strike Detector for Repeated Manual Work
Opened
#963 [Study] Solving the Perception Bottleneck — API-First Architecture on Apple Silicon
Opened
#965 Build Core ML UI state classifier for Morrowind
Opened
#964 Implement OpenMW Lua perception bridge (IPC layer)
Opened
#966 Implement three-tier metabolic LLM router (Qwen3-3B / Llama-8B / Qwen3-32B)
Opened
#968 Define GBNF grammar for constrained game-command decoding
Opened
#969 Build UESP RAG knowledge pipeline (ChromaDB + nomic-embed)
Opened
#967 Extract ESM data via tes3conv and build NetworkX navigation graph
Opened
#970 Implement MorrowindBehaviorTree engine for zero-cost routine actions
Opened
#971 Urgent: falsework and security and gitea database robustness
Opened
#972 [GOVERNING] Replacing Claude — Autonomous Research Pipeline Spec
Opened
#973 [P0] Implement web_fetch tool (trafilatura) in src/timmy/tools.py
Opened
#974 [P0] Create research prompt template library (skills/research/)
Opened
#977 [P1] Auto-create Gitea issues from research findings
Opened
#975 [P0] Build ResearchOrchestrator pipeline (src/timmy/research.py)
Opened
#976 [P1] Build semantic index for research outputs (nomic-embed-text + SQLite)
Opened
#981 [P2] Research sovereignty metrics + dashboard tracking
Opened
#979 [P2] Implement Kimi delegation for heavy research via Gitea labels
Opened
#980 [P2] Add Claude API fallback tier to cascade.py
Opened
#978 [P1] Integrate ResearchOrchestrator with Paperclip task runner
Opened
#982 [GOVERNING] Session Crystallization & Operational Playbook — Master Handoff Document
Opened
#983 Restore self-modification loop (deleted in Operation Darling Purge)
Opened
#984 Restore MCP integration via FastMCP v3.1.1 at /tools/mcp
Opened
#986 Extract sovereign tech stack manifest to machine-readable JSON
Opened
#985 Wire delegate_task to DistributedWorker for actual execution
Opened
#987 Implement content moderation pipeline (Llama Guard + game-context prompts)
Opened
#989 [URGENT] Deploy reverse proxy with TLS for Gitea (Nginx + Let's Encrypt)
Opened
#988 [URGENT] Disable Gitea registration + require sign-in to view
Opened
#990 [URGENT] Run Gitea backup before hardening changes
Opened
#993 [kimi-generated] Pre-existing test failures in dashboard calm and tools routes
Opened
#1008 Enhancement: Hardware-Accelerated "Perception" via Metal
Opened
#1006 Enhancement: Multi-Model "Consensus" Voting
Opened
#1011 Feature: Automated "Skill Discovery" Pipeline
Opened
#1007 Feature: Agent "Self-Correction" Dashboard
Opened
#1005 Feature: Agent "Internal Monologue" Visualizer
Opened
#1010 Enhancement: Nostr-based "Remote Kill Switch"
Opened
#1009 Feature: Agent "Energy Budget" Monitoring
Opened
#1018 Enhancement: Automated "Backlog Triage" via LLM
Opened
#1016 Enhancement: Secure "Air-Gapped" Mode
Opened
#1013 Feature: Agent "Emotional State" Simulation
Opened
#1015 Feature: Agent "Performance Regression" Suite
Opened
#1017 Feature: Agent "Voice" Customization UI
Opened
#1014 Enhancement: Local "Ollama" Model Auto-Updater
Opened
#1012 Enhancement: Integrated "Knowledge Graph" Explorer
Opened
#1019 Feature: Agent "Dreaming" Mode
Opened
#1056 Add content moderation pipeline (Llama Guard + game-context prompts)
Opened
#1063 [Study] Best Local Uncensored Agent Model for M3 Max 36GB
Opened
#1064 Install and configure Qwen3-14B Q5_K_M as Timmy primary brain
Opened
#1065 Implement Qwen3-8B / Qwen3-14B dual-model routing strategy
Opened
#1066 Run 5-test benchmark suite against local model candidates
Opened
#1067 Set up MCP bridge for Qwen3 via Ollama
Opened
#1068 Configure Dolphin 3.0 8B as creative writing fallback
Opened
#1069 Evaluate vllm-mlx as high-performance inference backend
Opened
#1070 [GOVERNING] Timmy as Autonomous Orchestrator — Vassal Protocol
Opened
#1071 Build Timmy autonomous backlog triage loop
Opened
#1072 Build agent dispatcher — route tasks to Claude Code, Kimi, APIs
Opened
#1073 Build Hermes health monitor — system resources + model management
Opened
#1074 [GOVERNING] Timmy Handoff — March 23, 2026 Operational Briefing
Opened
#1075 Integrate Claude Quota Monitor + Metabolic Protocol into cascade router
Opened
#1076 [GOVERNING] Deep Backlog Triage — Harness (Product) vs Infrastructure Separation
Opened
#1077 [EPIC] Kimi-Tasks Code Hygiene — Consolidated Refactoring & Tests
Opened
#1078 [EPIC] ASCII Video Showcase — Consolidated Demo Suite
Opened
#1079 [EPIC] Code Hygiene — Kimi Tasks + Refactoring Consolidation
Opened
#1080 [EPIC] ASCII Video Showcase — All Modes Consolidated
Opened
#1090 [EPIC] Nexus v1 — Timmy's Sovereign Home
Opened
#1091 [EPIC] Project Bannerlord — Timmy Becomes King of Calradia
Opened
#1092 [Bannerlord M0] Run Cognitive Benchmark on Hermes
Opened
#1093 [Bannerlord M1] Passive Lord — Observer Mode via GABS
Opened
#1095 [Bannerlord M3] Full Campaign Strategy — Economy, Diplomacy, Kingdom
Opened
#1094 [Bannerlord M2] Basic Campaign Actions — Move, Trade, Recruit
Opened
#1096 [Bannerlord M4] Formation Commander — Real-Time Battle Orders
Opened
#1097 [Bannerlord M5] King of Calradia — Sovereign Victory
Opened
#1098 [Bannerlord Infra] Windows VM Setup + GABS Mod Installation
Opened
#1099 [Bannerlord Research] Feudal Multi-Agent Hierarchy Integration Design
Opened
#1100 [AutoLoRA P0] Audit Hermes Agent Training Infrastructure
Opened
#1101 [AutoLoRA P0] Download and Test Hermes 4 Base Model
Opened
#1102 [AutoLoRA P1] Export Claude Conversation Trajectories
Opened
#1103 [AutoLoRA P1] LoRA Fine-Tune Hermes 4 on Exported Trajectories
Opened
#1104 [AutoLoRA P1] Load Fine-Tuned Model Back Into Hermes Harness
Opened
#1105 [AutoLoRA P2] Set Up Continuous Improvement Loop
Opened
#1106 [AutoLoRA P2] Integrate claude_quota.py Metabolic Protocol
Opened
#1112 [loop-generated] [bug] Pre-existing test failures block all commits via git hooks
Opened
#1114 [loop-generated] [bug] 10 pre-existing test failures on main block all commits — unhashable dict key
Opened
#1126 [loop-generated] [refactor] Break up mcp_bridge.py::_build_gitea_tools() — 137 lines
Opened
#1127 [loop-generated] [refactor] Break up scorecards.py — two functions over 100 lines each
Opened
#1128 [loop-generated] [feature] Implement 4 TODO stubs in timmyctl/cli.py
Opened
#1130 [loop-generated] [refactor] Add docstrings to 20 undocumented classes in src/
Opened
#1129 [loop-generated] [refactor] Clean up unused imports in memory_system.py
Opened
#1134 [loop-generated] [refactor] Break up mcp_bridge.py::_build_gitea_tools() — 137 lines
Opened
#1135 [loop-generated] [refactor] Break up mcp_bridge.py::run() — 129 lines
Opened
#1136 [loop-generated] [refactor] Break up dispatcher.py::_dispatch_via_gitea() — 110 lines
Opened
#1137 [loop-generated] [refactor] Break up dispatcher.py::dispatch_task() — 108 lines
Opened
#1138 [loop-generated] [test] Add unit tests for cascade.py — 1115 lines, 0 tests
Opened
#1139 [loop-generated] [test] Add unit tests for scorecard_service.py — 515 lines, 0 tests
Opened
#1149 [loop-generated] [bug] Main branch has 23 ruff lint errors — blocks all pushes
Opened
#1161 [loop-generated] [bug] tox -e format fails on main — 9 pre-existing ruff errors in bannerlord/
Opened
#1168 [loop-generated] [refactor] Break up cli.py::daily_run() — 105 lines
Opened
#1169 [loop-generated] [refactor] Break up cli.py::inbox() — 99 lines
Opened
#1170 [loop-generated] [refactor] Break up thinking.py::_maybe_file_issues() — 99 lines
Opened
#1171 [loop-generated] [refactor] Break up presence.py::produce_system_status() — 88 lines
Opened
#1172 [loop-generated] [test] Add unit tests for src/config.py — 599 lines, critical module
Opened
#1176 [kimi-generated] Pre-existing lint errors blocking PRs
Opened
#1177 [triage-generated] [bug] [P0] Fix GITEA_API default in triage_score.py and loop_guard.py — still pointing to localhost
Opened
#1181 [kimi-generated] kimi user lacks write permission for PR creation
Opened
#1185 [loop-generated] [refactor] Break up cascade.py::complete() — 84 lines
Opened
#1186 [loop-generated] [test] Add unit tests for daily_run.py — 435 lines, 0 tests
Opened
#1187 [loop-generated] [refactor] Break up vassal/dispatch.py::dispatch_issue() — 92 lines
Opened
#1191 [loop-generated] [test] Add unit tests for event bus (bus.py) — 356 lines, 0 tests
Opened
#1192 [loop-generated] [test] Add unit tests for chat_store.py — 155 lines, 0 tests
Opened
#1194 [loop-generated] [refactor] Break up produce_system_status() — 88 lines
Opened
#1193 [loop-generated] [test] Add unit tests for vassal/dispatch.py — 244 lines, 0 tests
Opened
#1195 [loop-generated] [test] Add unit tests for agent_health.py — 288 lines, 0 tests
Opened
#1208 Request for Timmy:
Opened
#1210 Please audit gitea activty and git branc history across the board for each repo
Opened
#1212 [loop-generated] [test] Add unit tests for events/bus.py — 356 lines, 0 tests
Opened
#1213 [loop-generated] [test] Add unit tests for router/metabolic.py — 424 lines, 0 tests
Opened
#1214 [loop-generated] [test] Add unit tests for vassal/orchestration_loop.py — 321 lines, 0 tests
Opened
#1215 [loop-generated] [refactor] Break up tools.py — 1032 lines, monolithic tool registry
Opened
#1217 Branch cleanup: delete ~20 stale/abandoned/duplicate branches
Opened
#1218 Rescue unmerged work: 3 branches contain real code with no open PR
Opened
#1219 Investigate: 5 PRs closed without merge on p0-critical open issues
Opened
#1220 Process: enforce one-agent-per-issue, auto-delete merged branches
Opened
#1223 Cross-repo: consolidate duplicate Nostr identity logic into shared library
Opened
#1236 [loop-generated] [test] Add unit tests for paperclip.py (173 lines, 0% coverage)
Opened
#1235 [loop-generated] [refactor] Delete dead code: tools_backup.py (1032 lines, zero imports)
Opened
#1237 [loop-generated] [test] Add unit tests for research_tools.py (46 lines, 0% coverage)
Opened
#1238 [loop-generated] [bug] 2 tests failing on main: test_three_strike_routes.py
Opened
#1243 [loop-generated] [bug] 10 vassal tests flaky under pytest-xdist parallel execution
Opened
#1247 [loop-generated] [bug] Pre-existing ruff lint errors block git hooks on all branches
Opened
#1249 [triage-generated] [bug] [P0] timmy chat crashes — ImportError: memory_write missing from memory_system
Opened
#1250 [triage-generated] [bug] [P0] Cycle-metrics pipeline dead — 0% success, all issue=null for 50+ cycles
Opened
#1256 [loop-generated] [bug] ruff format error on main: tests/timmy/test_autoresearch.py
Opened
#1259 [loop-generated] [hardening] perception_cache confidence threshold is hardcoded — should be configurable
Opened
#1260 [loop-generated] [test] Add unit tests for kimi_delegation.py — 350+ lines, critical delegation logic, 0 tests
Opened
#1261 [loop-generated] [test] Add unit tests for sovereignty/perception_cache.py — template matching with 0 tests
Opened
#1268 [loop-generated] [bug] Kimi produces empty commits — git add not called before commit
Opened
#1275 Screenshot dump for triage #1
Opened
#1277 [loop-generated] [refactor] Split memory_system.py — 1543 lines, extract subsystems
Opened
#1278 [loop-generated] [test] Add unit tests for orchestration_loop.py — untested core module
Opened
#1279 [loop-generated] [refactor] Split thinking.py — 1383 lines, second largest module
Opened
#1281 feat: add vLLM as alternative inference backend for improved agentic performance
Opened
#1282 feat: integrate SearXNG + Crawl4AI as self-hosted search backend for research agents
Opened
#1283 research: evaluate DeerFlow as autonomous research orchestration layer
Opened
#1284 chore: document and validate AirLLM Apple Silicon requirements in README/CLAUDE.md
Opened
#1285 chore: enforce "Normal Developer" discipline — tighten lint, type-check, and pre-push gates
Opened
#1293 [loop-generated] [test] Add unit tests for backlog_triage.py
Opened
#1292 [loop-generated] [test] Add unit tests for quest_system.py
Opened
#1294 [loop-generated] [test] Add unit tests for research_tools.py
Opened
#1295 [loop-generated] [test] Add unit tests for kimi_delegation.py
Opened
#1296 [loop-generated] [docs] Add module docstrings to 20+ undocumented files
Opened
#1304 [loop-generated] [bug] Stale issues polluting queue — completed work still open
Opened
#1314 [loop-generated] [test] Add unit tests for thinking/engine.py — 430 lines untested
Opened
#1315 [loop-generated] [test] Add unit tests for events/bus.py — 356 lines untested
Opened
#1316 [loop-generated] [test] Add unit tests for models/budget.py — 302 lines untested
Opened
#1329 [loop-generated] [bug] tests/scripts/test_llm_triage.py has syntax errors — broken on main
Opened
#1336 [loop-generated] [bug] test_cache_hit_skips_vlm times out on main (43s > 30s limit)
Opened
#1339 Do the thing
Opened
#1341 Task
Opened
#1340 Task
Opened
#1342 [loop-generated] [refactor] Split cascade.py — 1241 lines, largest module in codebase
Opened
#1343 [loop-generated] [test] Add unit tests for spark/engine.py — 406 lines untested
Opened
#1344 [loop-generated] [test] Add unit tests for memory/crud.py — 395 lines untested
Opened
#1345 [loop-generated] [test] Add unit tests for tools/system_tools.py — 357 lines untested
Opened
#1346 [loop-generated] [bug] 227 mypy errors — typecheck gate broken on main
Opened
#1351 Do the thing
Opened
#1360 [loop-generated] [refactor] Split dashboard/routes/world.py — 1065 lines, second largest module
Opened
#1361 [loop-generated] [test] Add unit tests for timmy/dispatcher.py — 917 lines mostly untested
Opened
#1362 [loop-generated] [test] Add unit tests for timmy/autoresearch.py — 645 lines mostly untested
Opened
#1363 [loop-generated] [refactor] Split dashboard/app.py — 780 lines, monolithic Flask app
Opened
#1364 [loop-generated] [refactor] Split timmy/backlog_triage.py — 761 lines, complex triage logic
Opened
#1365 [loop-generated] [test] Add unit tests for config.py — 746 lines, core configuration
Opened
#1366 [loop-generated] [test] Add unit tests for tools/_registry.py — 586 lines, tool registration
Opened
#1367 [loop-generated] [refactor] Split quest_system.py — 581 lines, game mechanics
Opened
#1368 [loop-generated] [optimization] Optimize voice_loop.py — 572 lines, performance critical
Opened
#1369 [loop-generated] [refactor] Split timmy/cli.py — 693 lines, monolithic CLI interface
Opened
#1370 [loop-generated] [refactor] Split infrastructure/hermes/monitor.py — 660 lines, system monitoring
Opened
#1371 [loop-generated] [test] Add unit tests for infrastructure/hermes/monitor.py — 660 lines untested
Opened
#1372 [loop-generated] [test] Add unit tests for integrations/chat_bridge/vendors/discord.py — 668 lines untested
Opened
#1374 [loop-generated] [test] Add unit tests for infrastructure/models/multimodal.py — 472 lines untested
Opened
#1375 [loop-generated] [refactor] Split integrations/chat_bridge/vendors/discord.py — 508 lines, Discord integration
Opened
#1373 [loop-generated] [test] Add unit tests for integrations/chat_bridge/vendors/discord.py — 508 lines untested
Opened
#1376 [loop-generated] [optimization] Optimize memory usage in cascade.py router — frequent allocation hotspot
Opened
#1378 [loop-generated] [soul-gap] Implement Bitcoin blockchain reading capability from SOUL.md
Opened
#1377 [loop-generated] [feature] Add health check endpoint for system monitoring
Opened
#1379 [loop-generated] [refactor] Split voice_loop.py — 572 lines, complex voice processing logic
Opened
#1382 [loop-generated] [test-coverage] Add tests for sovereignty/metrics.py — 413 lines, metrics collection untested
Opened
#1381 [loop-generated] [test-coverage] Add tests for infrastructure/models/router.py — 426 lines, routing logic untested
Opened
#1380 [loop-generated] [test-coverage] Add comprehensive tests for tools/_registry.py — 586 lines, zero coverage
Opened
#1383 [loop-generated] [refactor] Extract config.py sections — 746 lines, monolithic configuration
Opened
#1384 [loop-generated] [optimization] Profile and optimize memory usage in large modules
Opened
#1385 [loop-cycle-14] Refactor cascade.py - 1241 lines
Opened
#1386 [loop-cycle-14] Split dashboard/routes/world.py - 1065 lines
Opened
#1387 [loop-generated] [documentation] Create IMPLEMENTATION.md tracking SOUL.md gaps
Opened
#1388 [loop-generated] [refactor] Split timmy/dispatcher.py — 917 lines, agent dispatch orchestration
Opened
#1389 [loop-generated] [refactor] Split timmy/backlog_triage.py — 761 lines, autonomous backlog management
Opened
#1391 [loop-generated] [refactor] Split timmy/tools/_registry.py — 586 lines, tool management bottleneck
Opened
#1390 [loop-generated] [refactor] Split timmy/autoresearch.py — 645 lines, research orchestration
Opened
#1392 [loop-generated] [refactor] Split timmy/quest_system.py — 581 lines, goal management system
Opened
#1393 [loop-generated] [refactor] Split infrastructure/models/multimodal.py — 579 lines, AI model routing
Opened
#1394 [loop-generated] [refactor] Split timmy/mcp_bridge.py — 544 lines, MCP protocol integration
Opened
#1395 [loop-generated] [refactor] Split timmy/kimi_delegation.py — 538 lines, agent delegation system
Opened
#1396 [loop-generated] [performance] Profile and optimize database query patterns
Opened
#1397 [loop-generated] [infrastructure] Implement graceful shutdown and health checks
Opened
#1398 [loop-generated] [security] Implement comprehensive input validation and sanitization
Opened
#1399 [timmy-capability] Implement local model routing fallback chain
Opened
#1400 [soul-gap] Missing SOUL.md implementation in main Timmy instance
Opened
#1401 [loop-generated] [refactor] Split timmy/cli.py — 693 lines, command-line interface monolith
Opened
#1402 [loop-generated] [soul-gap] Implement graceful degradation from remote APIs to local models
Opened
#1403 [loop-generated] [performance] Implement request batching and connection pooling
Opened
#1404 [loop-generated] [feature] Add comprehensive system health monitoring and alerting
Opened
#1405 [loop-generated] [refactor] Split research.py — 528 lines, research coordination system
Opened
#1406 [loop-generated] [refactor] Split scorecard_service.py — 517 lines, dashboard scorecard logic
Opened
#1407 [loop-generated] [security] Split moderation.py — 497 lines, content filtering system
Opened
#1408 [loop-generated] [performance] Implement async/await patterns for I/O operations
Opened
#1409 [Refactor] Implement Exponential Backoff with Jitter in Agent API Calls
Opened
#1410 [CI/CD] Automate Cleanup of Stale Agent Worktrees via Cron
Opened
#1411 [Resilience] Agent Crash Recovery: Persist Current Context Before Fatal Escapes
Opened
#1412 [Feature] Dynamic Agent Auto-scaling Based on Open Issues Queue Length
Opened
#1413 [Infrastructure] Containerize Agent Dispatch Loops for Isolation and Reproducibility
Opened
#1414 [Feature] Graceful Degradation: Fallback to Cheaper LLM If Primary Hits Rate Limits
Opened
#1415 [Bug] Fix kimi-loop.sh Gitea Filter Bug Properly Using GraphQL Or Extended Query Params
Opened
#1416 [Refactor] Refactor ops-helpers.sh into Modulated Command-Line Interface
Opened
#1417 [Refactor] Unify Skip List Logic Across All Agent Loops into a Shared Library
Opened
#1418 [Security] Extract Magic Strings and Hardcoded IPs into Configuration Variables
Opened
#1419 [Optimization] Triage Loop Resource Optimization: Parallelize Batch Scraping
Opened
#1420 [Security] Secure Hardcoded API Tokens in ~/.hermes Using Secrets Management
Opened
#1421 [Security] Develop an Automatic Token Rotation Script for Gitea Agent Credentials
Opened
#1422 [Security] Enforce Branch Protections that Auto-Reject Agent PRs Flagged with Potential Secrets
Opened
#1423 [Observability] Centralized Agent Telemetry: Route Logs to an ELK or Loki Stack
Opened
#1424 [Observability] Dashboard System Health Monitor: Status Page for All Agent Subsystems
Opened
#1425 [Observability] loop_guard.py: Detect Deadlocks and Kill Zombie Python Processes Faster
Opened
#1426 [CI/CD] Introduce Dependency Caching in .gitea/workflows CI/CD Pipelines
Opened
#1427 [Bug] claude-loop.sh Workspace Collision Fix: Use UUIDs for Concurrent Worktree Checkouts
Opened
#1428 [Quality] Establish Standard Linter Configuration for Agent PR Approvals
Opened
#1429 [Quality] Add Mock Integration Tests Emulating Gitea API Responses for Loop Scripts
Opened
#1430 [loop-generated] [refactor] Split timmy/memory/crud.py — 395 lines, memory operations bottleneck
Opened
#1431 [loop-generated] [optimization] Optimize sovereignty loop performance — 379 lines, core sovereignty validation
Opened
#1432 [loop-generated] [reliability] Consolidate error handling patterns — improve system resilience
Opened
#1433 Do the thing
Opened
#1434 Task
Opened
#1435 Task
Opened
#1436 [loop-generated] [optimization] Optimize Docker build pipeline — reduce image size and build time
Opened
#1437 [loop-cycle-28] [refactor] Split cascade.py — 1241 lines, largest module in codebase
Opened
#1439 [loop-generated] [reliability] Implement Circuit Breaker Pattern for External Dependencies
Opened
#1440 [loop-generated] [soul-gap] Implement Local Model Priority Routing - SOUL Sovereignty Violation
Opened
#1441 Do the thing
Opened
#1442 [loop-generated] [soul-gap] Create Missing SOUL.md at Repository Root - CRITICAL
Opened
#1443 [loop-generated] [refactor] Split config.py — 747 lines, system configuration bottleneck
Opened
#1444 [loop-generated] [soul-gap] Implement Local-First Model Routing with External Fallback Only
Opened
#1445 [loop-generated] [optimization] Implement Memory Profiling and Optimization for Large Modules
Opened
#1446 Do the thing
Opened
#1447 [loop-generated] [bug] Kimi loop stalled - 50 issues assigned, 0 PRs delivered
Opened
#1450 [loop-generated] [refactor] Split dispatcher.py — 917 lines, largest remaining module
Opened
#1452 [loop-generated] [refactor] Split discord.py — 668 lines, vendor chat integration
Opened
#1451 [loop-generated] [refactor] Split backlog_triage.py — 761 lines, complex triage logic
Opened
#1453 [loop-generated] [refactor] Split monitor.py — 660 lines, hermes infrastructure monitoring
Opened
#1454 [loop-generated] [refactor] Split autoresearch.py — 645 lines, auto-research pipeline
Opened
#1459 [loop-generated] [bug] Pre-push hook times out on agentic_loop test (Ollama connection)
Opened
#1460 [loop-generated] [bug] Gitea API assignee filter broken — returns all issues regardless of parameter
Opened
#1463 [triage-generated] [bug] triage_score.py overwrites curated queue every 5 cycles — undoes all triage work
Opened
#1462 [triage-generated] [bug] Loop never writes cycle_result.json — 0% success rate is measurement bug
Opened
#1470 [triage-generated] [bug] Dev loop picks closed issues - must verify state before starting work
Opened
#1471 [triage-generated] [bug] test_creates_db_file fails on main - blocks CI
Opened
#1472 [triage-generated] [bug] Repo was archived causing mass-close of all issues - add safeguard
Opened
#1473 [triage-generated] [task] Audit mass-closed issues and reopen unfinished work
Opened
#1474 [EPIC] Timmy Self-Improvement — April 2026
Opened
#1475 [SELF-IMPROVE] Dead-man switch for burn cycles — alert when cron runs but produces no log output
Opened
#1477 [SELF-IMPROVE] CI testbed dead-man alert — auto-file p0 when 67.205.155.108 unreachable
Opened
#1476 [SELF-IMPROVE] Morning report compiler — aggregate burn-logs into daily brief at 6 AM
Opened
#1478 [SELF-IMPROVE] Config drift detector — compare local config.yaml against timmy-config repo
Opened
#1479 [SELF-IMPROVE] Session DB auto-pruning — compress old sessions, enforce growth limit
Opened
#1480 [REPORT] OpenProse Extraction — Prose Workflows as Force Multiplier