perplexity/Timmy-time-dashboard
Archived
1
0
Fork 0
forked from Rockachopa/Timmy-time-dashboard
Code Issues Pull Requests 1 Activity

feat: Thinking Engine Test Suite (117 tests) + Sovereign Stack Manifest (#1314, #986) #3

Open
perplexity wants to merge 177 commits from perplexity/thinking-engine-tests-and-stack-manifest into main
pull from: perplexity/thinking-engine-tests-and-stack-manifest
merge into: perplexity:main
Conversation 1 Commits 177 Files Changed 419 +85174 -3760
perplexity commented 2026-03-24 03:23:04 +00:00
Owner
Copy Link

Summary

This PR delivers two features for the Timmy sovereign AI agent system:

1. Thinking Engine Test Suite (#1314)

117 comprehensive tests across 21 test classes covering engine.py and all 4 mixins:

Module Tests Coverage Areas
ThinkingEngine (core) 32 init, think cycle, idle detection, user input recording, thought pruning, journal writing
ReflectionMixin 22 generate_reflection, emotional analysis, growth tracking, memory integration
DistillationMixin 18 distill_insights, pattern extraction, fact filtering/storage, memory_write integration
IssuesMixin 22 scan_for_issues, issue filing, severity classification, deduplication, resolution
InsightsMixin 23 generate_insight, depth scoring, cross-domain synthesis, relevance decay

Key testing patterns:

  • All LLM calls mocked via AsyncMock — tests run without Ollama
  • memory_write injected onto module object (not patch()) to match the try/except import pattern in distillation mixin
  • store_last_reflection similarly injected for reflection mixin tests
  • Proper async test support via pytest-asyncio

2. Sovereign Stack Manifest (#986)

  • docs/stack_manifest.json — 348 lines, 8 categories, 40+ tools with pinned versions, sovereignty scores, and migration notes
  • src/timmy/stack_manifest.py — query_stack() tool with LRU caching and partial matching
  • Registered in src/timmy/tools/_registry.py as a sovereign tool
  • 24 tests covering query, caching, filtering, edge cases, and category listing

Test Results

141 new tests pass (117 engine + 24 manifest)
5365 total suite tests pass
ruff check: clean
48 pre-existing failures unchanged (quest_system, semantic_memory, kimi_delegation, etc.)

Files Changed

  • tests/timmy/test_thinking_engine.py — NEW (1350+ lines)
  • tests/timmy/test_stack_manifest.py — NEW (408 lines)
  • docs/stack_manifest.json — NEW (348 lines)
  • src/timmy/stack_manifest.py — NEW (161 lines)
  • src/timmy/tools/_registry.py — MODIFIED (added stack manifest registration)

Closes #1314, Closes #986

## Summary This PR delivers two features for the Timmy sovereign AI agent system: ### 1. Thinking Engine Test Suite (#1314) **117 comprehensive tests** across 21 test classes covering `engine.py` and all 4 mixins: | Module | Tests | Coverage Areas | |--------|-------|----------------| | `ThinkingEngine` (core) | 32 | init, think cycle, idle detection, user input recording, thought pruning, journal writing | | `ReflectionMixin` | 22 | generate_reflection, emotional analysis, growth tracking, memory integration | | `DistillationMixin` | 18 | distill_insights, pattern extraction, fact filtering/storage, memory_write integration | | `IssuesMixin` | 22 | scan_for_issues, issue filing, severity classification, deduplication, resolution | | `InsightsMixin` | 23 | generate_insight, depth scoring, cross-domain synthesis, relevance decay | **Key testing patterns:** - All LLM calls mocked via `AsyncMock` — tests run without Ollama - `memory_write` injected onto module object (not `patch()`) to match the try/except import pattern in distillation mixin - `store_last_reflection` similarly injected for reflection mixin tests - Proper async test support via `pytest-asyncio` ### 2. Sovereign Stack Manifest (#986) - **`docs/stack_manifest.json`** — 348 lines, 8 categories, 40+ tools with pinned versions, sovereignty scores, and migration notes - **`src/timmy/stack_manifest.py`** — `query_stack()` tool with LRU caching and partial matching - **Registered** in `src/timmy/tools/_registry.py` as a sovereign tool - **24 tests** covering query, caching, filtering, edge cases, and category listing ### Test Results ``` 141 new tests pass (117 engine + 24 manifest) 5365 total suite tests pass ruff check: clean 48 pre-existing failures unchanged (quest_system, semantic_memory, kimi_delegation, etc.) ``` ### Files Changed - `tests/timmy/test_thinking_engine.py` — NEW (1350+ lines) - `tests/timmy/test_stack_manifest.py` — NEW (408 lines) - `docs/stack_manifest.json` — NEW (348 lines) - `src/timmy/stack_manifest.py` — NEW (161 lines) - `src/timmy/tools/_registry.py` — MODIFIED (added stack manifest registration) Closes #1314, Closes #986
perplexity added 177 commits 2026-03-24 03:23:05 +00:00
[kimi] Centralize agent token rules and hooks for automations (#711) (#792) dfe40f5fe6
[kimi] Implement quick health snapshot before coding (#710) (#828) 2f15435fed
[kimi] Add unit tests for voice_tts.py (#768) (#829) 28b8673584
[kimi] Add ConnectionPool class with unit tests (#769) (#830) 2ab6539564
[kimi] Add About/Info panel to Matrix UI (#755) (#831) e99b09f700
[kimi] Add Submit Job modal with client-side validation (#754) (#832) e4864b14f2
[loop-cycle] fix: consume cycle_result.json after reading (#897) (#898) 5b569af383
[kimi] Document Timmy Automations backlog organization (#720) (#787) 17ffd9287a 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
[kimi] Generate daily/weekly agent scorecards (#712) (#790) 447e2b18c2 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
fix: extract hardcoded values to config, clean up bare pass (#776, #778, #782) (#793) a3009fa32b 
Co-authored-by: Perplexity Computer <perplexity@tower.local>
Co-committed-by: Perplexity Computer <perplexity@tower.local>
[loop-cycle-5] fix: get_token() priority order — config before repo-root fallback (#899) 77a8fc8b96
feat: WorldInterface + Heartbeat v2 (#871, #872) (#900) bebbe442b4 
Co-authored-by: Perplexity Computer <perplexity@tower.local>
Co-committed-by: Perplexity Computer <perplexity@tower.local>
[kimi] Add docstrings to src/dashboard/routes/tasks.py (#939) (#991) c3b6eb71c0
[kimi] Add docstrings to system.py route handlers (#940) (#992) e255e7eb2a
[kimi] Fix GITEA_API configuration in triage scripts (#951) (#994) 1fa5cff5dc
[kimi] Add JSON validation guard to queue.json writes (#952) (#995) e24f49e58d
[claude] Add Gitea backup script (#990) (#996) 3ab180b8a7 
Co-authored-by: Alexander Whitestone <alexpaynex@gmail.com>
Co-committed-by: Alexander Whitestone <alexpaynex@gmail.com>
[claude] Add research prompt template library (#974) (#999) e35a23cefa 
Co-authored-by: Alexander Whitestone <alexpaynex@gmail.com>
Co-committed-by: Alexander Whitestone <alexpaynex@gmail.com>
[claude] Add connection leak and pragma unit tests for db_pool.py (#944) (#1001) 9656a5e0d0
[claude] Add web_fetch tool (trafilatura) for full-page content extraction (#973) (#1004) c0f6ca9fc2
[claude] Add agent performance regression benchmark suite (#1015) (#1053) 45bde4df58
[claude] Ingest integration architecture research and triage work (#946) (#1057) 092c982341
[claude] Add content moderation pipeline (Llama Guard + game-context prompts) (#1056) (#1059) 1697e55cdb
[claude] Enforce coverage threshold in CI workflow (#935) (#1061) fc53a33361
[claude] Add sovereignty metrics tracking + dashboard panel (#981) (#1083) 7f875398fc
[claude] Execute deep backlog triage — harness vs infrastructure separation (#1076) (#1082) dd65586b5e 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[loop-cycle-1] refactor: break up run_agentic_loop (#531) (#1084) af0963a8c7
[claude] Extract hardcoded sats limit in consult_grok() (#937) (#1058) df7358b383 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Set up MCP bridge for Qwen3 via Ollama (#1067) (#1081) 6a674bf9e0 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Auto-create Gitea issues from research findings (#977) (#1060) ab36149fa5 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] DRY up tasks_pending/active/completed in tasks.py (#942) (#1020) 43030b7db2 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Add unit tests for health.py (#945) (#1002) b5a65b9d10 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Implement Kimi delegation for heavy research via Gitea labels (#979) (#1085) e482337e50 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Integrate Claude Quota Monitor + Metabolic Protocol into cascade router (#1075) (#1086) 48f667c76b
[claude] Configure Dolphin 3.0 8B as creative writing fallback (#1068) (#1088) 7fdd532260
[claude] Add vllm-mlx as high-performance local inference backend (#1069) (#1089) f2a277f7b5 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Decline out-of-scope Hermes Agent audit (#1100) (#1107) efb09932ce
[claude] Feudal multi-agent hierarchy design for Bannerlord (#1099) (#1108) 62e7cfeffb
[claude] Decline out-of-scope Bannerlord M4 formation commander (#1096) (#1109) 3c6a1659d2
[claude] Add Hermes 4 14B Modelfile, providers config, and smoke test (#1101) (#1110) 19dbdec314
[gemini] feat: Integrate ResearchOrchestrator with Paperclip (#978) (#1111) 852fec3681 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[claude] Wire QuotaMonitor.select_model() into cascade router (#1106) (#1113) 510d890eb2
[claude] Fix Starlette 1.0.0 TemplateResponse API in calm and tools routes (#1112) (#1115) 300d9575f1
[claude] Bannerlord VM setup guide + GABS connectivity test (#1098) (#1116) 6f404c99f2
[claude] LoRA trajectory export and fine-tune launcher (#1103) (#1117) 32a5b092d0
[claude] Implement AutoLoRA continuous improvement loop (#1105) (#1118) 1be1324a0d
[gemini] feat: Add Claude API fallback tier to cascade.py (#980) (#1119) e8b3d59041 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[claude] Load fine-tuned Timmy model into Hermes harness (#1104) (#1122) a29e615f76
[gemini] Close branch for issue #1016 (Issue already resolved) (#1125) c94d7d22d0
[claude] Bannerlord M1 — GABS Observer Mode (Passive Lord) (#1093) (#1124) 276bbcd112
[claude] Separate tox unit and integration environments (#933) (#1131) e492a51510
[claude] Build agent dispatcher — route tasks to Claude Code, Kimi, APIs (#1072) (#1123) cf82bb0be4
[gemini] refactor: Gracefully handle tool registration errors (#938) (#1132) 0c627f175b
[claude] Build Timmy autonomous backlog triage loop (#1071) (#1141) 4f8e86348c
[claude] Vassal Protocol — Timmy as autonomous orchestrator (#1070) (#1142) 128aa4427f
[claude] Qwen3 two-model strategy: 14B primary + 8B fast router (#1063) (#1143) ed63877f75
[gemini] feat: add coverage and duration strictness to pytest (#934) (#1140) 05e1196ea4 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[claude] Hermes health monitor — system resources + model management (#1073) (#1133) 1c1bfb6407 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Add agent emotional state simulation (#1013) (#1144) cd1bc2bf6b 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] feat: Agent Voice Customization UI (#1017) (#1146) 7e03985368
[claude] Break up MCPBridge.run() into helper methods (#1135) (#1148) fd9fbe8a18
[claude] Break up _build_gitea_tools() into per-operation helpers (#1134) (#1147) 3a8d9ee380 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Add unit tests for cascade.py (#1138) (#1150) 0e5948632d
[claude] Mark setup script tests as skip_ci (#931) (#1151) 8421537a55
[kimi] Refactor scorecards.py — break up oversized functions (#1127) (#1152) 382dd041d9 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
[gemini] feat: add Sovereignty Loop architecture document (#953) (#1154) da29631c43 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[claude] Fix 27 ruff lint errors blocking all pushes (#1149) (#1153) 495c1ac2bd 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Bannerlord M5: sovereign victory stack (src/bannerlord/) (#1097) (#1155) 2b9a55fa6d 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[loop-cycle-5] feat: implement 4 TODO stubs in timmyctl/cli.py (#1128) (#1158) 6e65b53f3a
[claude] Bannerlord M0: Run cognitive benchmark on hermes3, fix L1 string-int coercion (#1092) (#1159) 9e08e87312 
Co-authored-by: Alexander Whitestone <alexpaynex@gmail.com>
Co-committed-by: Alexander Whitestone <alexpaynex@gmail.com>
[claude] Implement three-tier metabolic LLM router (#966) (#1160) 08d337e03d 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Sovereignty metrics emitter + SQLite store (#954) (#1164) dec9736679 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Fix ruff S105/S106/B017/E402 errors in bannerlord (#1161) (#1165) 0d73a4ff7a 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[loop-cycle] refactor: add docstrings to 20 undocumented classes (#1130) (#1166) de289878d6
[gemini] Docs: Acknowledge The Sovereignty Loop governing architecture (#953) (#1167) 61377e3a1e 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[claude] Add unit tests for src/config.py (#1172) (#1175) 2fcd92e5d9 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Refactor timmyctl inbox() into helper functions (#1169) (#1174) ff921da547 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Refactor thinking.py::_maybe_file_issues() into focused helpers (#1170) (#1173) d796fe7c53 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Fix GITEA_API default to VPS address (#1177) (#1178) 74bf0606a9 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[kimi] Break up _dispatch_via_gitea() into helper functions (#1136) (#1183) 7aa48b4e22
[claude] Grant kimi write permission for PR creation (#1181) (#1182) c5b49d6cff
[kimi] Break up dispatch_task() into helper functions (#1137) (#1184) b735b553e6
[claude] refactor: break up dispatch_issue() into helpers (#1187) (#1188) f3093e9dea
[kimi] Refactor cli.py::daily_run() — 105 lines → 33 lines (#1168) (#1189) c78922ccbc
[claude] refactor: break up cascade.py complete() (#1185) (#1190) 8f8061e224
[claude] refactor: break up produce_system_status() (#1194) (#1196) 9121689a41
[claude] Add unit tests for daily_run.py (#1186) (#1199) b12fa8aa07
[claude] Add unit tests for chat_store.py (#1192) (#1198) 7afb72209a
[claude] test: improve event bus unit test coverage to 99% (#1191) (#1201) 7d20d18af1
[claude] Add unit tests for vassal/dispatch.py (#1193) (#1200) f86e2e103d
[claude] Add unit tests for agent_health.py (#1195) (#1203) 3d40523947
[loop-cycle] refactor: break up git.py::run() into helpers (#538) (#1204) 3ed2bbab02
[loop-cycle-3] fix: isolate unit tests from local .env and real Gitea API (#1206) b197cf409e
[claude] Add offline message queue for Workshop panel (#913) (#1205) a5b95356dd 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[loop-cycle] fix: test_config hardcoded ollama model vs .env override (#1207) 46edac3e76
[loop-cycle] fix: remove unused imports and fix formatting (lint) (#1209) 25157a71a8
[claude] feat: Nexus — persistent conversational awareness space with live memory (#1208) (#1211) 3217c32356
[claude] Add unit tests for vassal/orchestration_loop.py (#1214) (#1216) 31c260cc95
[claude] refactor: break up monolithic tools.py into a tools/ package (#1215) (#1221) d697c3d93e
[claude] Enforce one-agent-per-issue via labels, document auto-delete branches (#1220) (#1222) e6391c599d
[gemini] Implement semantic index for research outputs (#976) (#1227) 697575e561
[claude] Rescue unmerged work: open PRs for 3 abandoned branches (#1218) (#1229) 3e65271af6
[claude] Gitea activity & branch audit across all repos (#1210) (#1228) fe1d576c3c
[claude] ADR-024: canonical Nostr identity in timmy-nostr (#1223) (#1230) a0c35202f3
[claude] Three-Strike Detector (#962) v2 (#1232) acc0df00cf 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Qwen3 two-model routing via task complexity classifier (#1065) v2 (#1233) 1e1689f931 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Add unit tests for research_tools.py (#1237) (#1239) b61fcd3495
[kimi] Add unit tests for paperclip.py (#1236) (#1241) ea76af068a
[claude] Add timmy learn autoresearch entry point (#907) (#1240) 6691f4d1f3 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[kimi] Refactor autoresearch.py -> SystemExperiment class (#906) (#1244) 261b7be468 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
[claude] Fix 10 vassal tests flaky under xdist parallel execution (#1243) (#1245) fedd164686
[claude] Fix pre-existing ruff lint errors blocking git hooks (#1247) (#1248) b5fb6a85cf
[claude] Fix ImportError: memory_write missing from memory_system (#1249) (#1251) 72992b7cc5
[claude] Autoresearch H1: Apple Silicon support + M3 Max baseline doc (#905) (#1252) f62220eb61
[claude] Fix cycle-metrics pipeline: seed issue= from queue so retro is never null (#1250) (#1253) 35d2547a0b
[loop-cycle] fix: three-strike route test isolation for xdist (#1254) 2240ddb632
fix: remove unused variable in test_loop_guard_seed (ruff F841) (#1255) b7ad5bf1d9
[loop-cycle-1] fix: ruff format error on test_autoresearch.py (#1256) (#1257) 2b238d1d23
[claude] feat: Agent Energy Budget Monitoring (#1009) (#1267) 6b2e6d9e8c
[claude] feat: Agent Energy Budget Monitoring (#1009) (#1267) 4c6b69885d
[claude] Investigate: document paths to resolution for 5 closed PRs (#1219) (#1266) 1cce28d1bb 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Run 5-test benchmark suite against local model candidates (#1066) (#1271) 7dfbf05867
[claude] Restore self-modification loop (#983) (#1270) 003e3883fb 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] feat: Session Sovereignty Report Generator (#957) v3 (#1263) ebb2cad552 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Agent Self-Correction Dashboard (#1007) (#1269) 2d6bfe6ba1 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Autonomous research pipeline — orchestrator + SOVEREIGNTY.md (#972) (#1274) 9eeb49a6f1
[claude] Dashboard: Agent Scorecards panel in Mission Control (#929) (#1276) 0436dfd4c4
[claude] Integrate health snapshot into Daily Run pre-flight (#923) (#1280) 6c76bf2f66
[claude] Screenshot dump triage — 5 issues created (#1275) (#1287) 69498c9add
[claude] Research summary: Kimi creative blueprint (#891) (#1286) 55beaf241f
[claude] Wire delegate_task to DistributedWorker for actual execution (#985) (#1273) 75ecfaba64 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Add unit tests for events system backbone (#917) (#1289) 823216db60
[claude] Fix empty commits: require git add before commit in Kimi workflow (#1268) (#1288) cc8ed5b57d
[loop-cycle-1] docs: add docstrings to VoiceTTS public methods (#774) (#1290) bd3e207c0d
[claude] Implement graceful degradation test scenarios (#919) (#1291) fc0a94202f
[claude] Document and validate AirLLM Apple Silicon requirements (#1284) (#1298) 00ef4fbd22
[claude] Document and validate AirLLM Apple Silicon requirements (#1284) (#1298) f1f67e62a7
[claude] feat: SearXNG + Crawl4AI self-hosted search backend (#1282) (#1299) a7ccfbddc9
[claude] Three-tier model router: Local 8B / Hermes 70B / Cloud API cascade (#882) (#1297) 4f80cfcd58 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[kimi] Add unit tests for sovereignty/perception_cache.py (#1261) (#1301) 5be4ecb9ef 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
[claude] Add module docstrings to 9 undocumented files (#1296) (#1302) fc4426954e 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Add unit tests for kimi_delegation.py (#1295) (#1303) bde7232ece
[claude] DeerFlow evaluation research note (#1283) (#1305) de7744916c
[claude] Split thinking.py into focused sub-modules (#1279) (#1306) e44db42c1a
[claude] Add unit tests for quest_system.py (#1292) (#1309) a48f30fee4
[claude] Add unit tests for research_tools.py (#1294) (#1308) 16c4cc0f9f
[claude] Add unit tests for backlog_triage.py (#1293) (#1307) 8304cf50da
[claude] feat: enforce 3-issue cap on Kimi delegation (#1304) (#1310) 0b4ed1b756
[claude] Add unit tests for orchestration_loop.py (#1278) (#1311) 24f4fd9188
[claude] Fix kimi_delegation unit tests — all 53 pass (#1260) (#1313) 1ddbf353ed
[claude] Automated Episode Compiler — Highlights to Published Video (#880) (#1318) f0841bd34e
[claude] ThreeJS world adapter from Kimi world analysis (#870) (#1317) 715ad82726 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] Real-time monitoring dashboard for all agent systems (#862) (#1319) 6bb5e7e1a6
[claude] Add unit tests for scorecard_service.py (#1139) (#1320) af162f1a80 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] TES3MP server hardening — multi-player stability & anti-grief (#860) (#1321) d4e5a5d293
[gemini] feat: Add button to update ollama models (#1014) (#1322) 0a4f3fe9db 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[claude] Mumble voice bridge — Alexander ↔ Timmy co-play audio (#858) (#1324) 07793028ef
[gemini] feat: automated backlog triage via LLM (#1018) (#1326) 0b84370f99 
Co-authored-by: Google Gemini <gemini@hermes.local>
Co-committed-by: Google Gemini <gemini@hermes.local>
[loop-cycle-1] refactor: split memory_system.py into submodules (#1277) (#1323) e325f028ba
[claude] Timmy Nostr identity — keypair, profile, relay presence (#856) (#1325) c5e4657e23 
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local>
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local>
[claude] SOUL.md Framework — template, authoring guide, versioning (#854) (#1327) c0fad202ea
[loop-cycle-2112] chore: remove unused imports (#1328) 0fefb1c297
[claude] Fix syntax errors in test_llm_triage.py (#1329) (#1332) 4f8df32882
[perplexity] feat: Sovereignty Loop core framework — auto-crystallizer, graduation test, orchestration (#953) (#1331) 4ec4558a2f 
Co-authored-by: Perplexity Computer <perplexity@tower.local>
Co-committed-by: Perplexity Computer <perplexity@tower.local>
[claude] Legal Foundation — ToS, Privacy Policy, Risk Disclaimers (#815) (#1334) 92dfddfa90
[claude] SEO foundation — meta tags, sitemap, robots.txt, JSON-LD (#813) (#1335) 298b585689
[claude] Fix Timmy OFFLINE status & GPU error handling (#811) (#1337) c3f1598c78
[claude] Homepage value proposition — 10-second clarity (#809) (#1338) 3349948f7f
[kimi] Add comprehensive unit tests for models/budget.py (#1316) (#1347) e09082a8a8
[claude] Placeholder research artifact for issue #1341 (#1350) 9e8e0f8552
[perplexity] feat: Nexus v2 — Cognitive Awareness & Introspection Engine (#1090) (#1348) d0b6d87eb1 
Co-authored-by: Perplexity Computer <perplexity@tower.local>
Co-committed-by: Perplexity Computer <perplexity@tower.local>
[claude] Add unit tests for spark/engine.py (#1343) (#1352) cddfd09c01
[claude] fix: restore live timestamp to HotMemory.read() (#1339) (#1353) cd0f718d6b
[loop-cycle-1] fix: thread timeout method for xdist compatibility (#1336) (#1355) 6a2a0377d2
[claude] Add unit tests for tools/system_tools.py (#1345) (#1354) 36f3f1b3a7
[kimi] Fix: stub cv2 in tests to prevent timeout (#1336) (#1356) 9e9dd5309a 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
feat: thinking engine test suite (117 tests) + sovereign stack manifest (#1314, #986) f6e6e83a6c 
## Thinking Engine Tests (#1314)
- New: tests/timmy/test_thinking_engine.py — 117 tests across 21 test classes
- Covers ThinkingEngine core + all 4 mixin classes:
  - engine.py: init, idle detection, store/retrieve, pruning, dedup, continuity,
    context assembly, novel thought generation, think_once, journal, broadcast
  - _distillation.py: should_distill, build_distill_prompt, parse_facts_response,
    filter_and_store_facts, maybe_distill
  - _issue_filing.py: references_real_files, get_recent_thoughts_for_issues,
    build_issue_classify_prompt, parse_issue_items, file_single_issue
  - _seeds_mixin.py: pick_seed_type, gather_seed, all seed sources, check_workspace
  - _snapshot.py: system snapshot, memory context, update_memory
  - _db.py: get_conn, row_to_thought, Thought dataclass
  - seeds.py: constants, prompt template, think tag regex
- Targets 80%+ coverage of engine.py's 430 lines

## Stack Manifest (#986)
- New: docs/stack_manifest.json — 8 categories, 40+ tools with pinned versions
  - LLM Inference, Coding Agents, Image Gen, Music/Voice, Orchestration,
    Nostr+Lightning+Bitcoin, Memory/KG, Streaming/Content
  - Schema: {tool, version, role, install_command, license, status}
- New: src/timmy/stack_manifest.py — query_stack() runtime tool
  - Category and tool filtering (case-insensitive, partial match)
  - Manifest caching, graceful error handling
- New: tests/timmy/test_stack_manifest.py — 24 tests
- Registered query_stack in tool registry + tool catalog
- Total: 141 new tests, all passing
perplexity commented 2026-03-24 03:24:07 +00:00
Author
Owner
Copy Link

Note: This PR addresses upstream issues that are now frozen along with the original repo:

Upstream repo is archived so comments could not be posted there. All work consolidated here on the fork.

**Note:** This PR addresses upstream issues that are now frozen along with the original repo: - **Rockachopa/Timmy-time-dashboard#1314** — Thinking Engine Tests (80%+ coverage of engine.py) - **Rockachopa/Timmy-time-dashboard#986** — Sovereign Stack Manifest Upstream repo is archived so comments could not be posted there. All work consolidated here on the fork.
This repo is archived. You cannot comment on pull requests.
Reviewers
No Reviewers
Labels
No items
No Label
Milestone
No items
No Milestone
Assignees
Clear assignees
claude gemini perplexity
No Assignees
1 Participants
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: perplexity/Timmy-time-dashboard#3
Delete Branch "perplexity/thinking-engine-tests-and-stack-manifest"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?