Alexander Whitestone
283ec330c8
feat: implement AutoLoRA continuous improvement loop ( #1105 )
...
Tests / lint (pull_request) Failing after 16s
Tests / test (pull_request) Has been skipped
Adds the weekly sovereignty retrain cycle — Timmy improves himself
without cloud AI in the decision path.
Components:
- `timmy_automations/retrain/trajectory_exporter.py` — reads session
JSONL logs and segments them into discrete conversation trajectories
- `timmy_automations/retrain/quality_filter.py` — scores trajectories
(multi-step tasks, successful tool calls, decision points) and keeps
only HIGH/MEDIUM quality examples
- `timmy_automations/retrain/training_dataset.py` — appends filtered
trajectories to a chat-format JSONL training file with deduplication
- `timmy_automations/retrain/lora_trainer.py` — triggers mlx_lm.lora
fine-tune and registers the resulting adapter in Ollama; degrades
gracefully when mlx-lm is unavailable
- `timmy_automations/retrain/training_log.py` — records per-cycle
metrics (iteration count, train loss, skill accuracy) to JSONL + MD
- `timmy_automations/retrain/retrain.py` — main orchestrator; runs the
full pipeline and is registered as a `weekly_sunday` automation
Automation registered in `automations.json` as `retrain` with
`schedule: weekly_sunday` pointing to `hermes4-14b` as the base model.
49 new unit tests covering all components.
Fixes #1105
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com >
2026-03-23 14:17:39 -04:00
19dbdec314
[claude] Add Hermes 4 14B Modelfile, providers config, and smoke test ( #1101 ) ( #1110 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 17:59:45 +00:00
3c6a1659d2
[claude] Decline out-of-scope Bannerlord M4 formation commander ( #1096 ) ( #1109 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 17:59:18 +00:00
62e7cfeffb
[claude] Feudal multi-agent hierarchy design for Bannerlord ( #1099 ) ( #1108 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 17:57:32 +00:00
efb09932ce
[claude] Decline out-of-scope Hermes Agent audit ( #1100 ) ( #1107 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 17:56:16 +00:00
f2a277f7b5
[claude] Add vllm-mlx as high-performance local inference backend ( #1069 ) ( #1089 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:34:13 +00:00
7fdd532260
[claude] Configure Dolphin 3.0 8B as creative writing fallback ( #1068 ) ( #1088 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 15:25:06 +00:00
48f667c76b
[claude] Integrate Claude Quota Monitor + Metabolic Protocol into cascade router ( #1075 ) ( #1086 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 15:18:11 +00:00
e482337e50
[claude] Implement Kimi delegation for heavy research via Gitea labels ( #979 ) ( #1085 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:14:53 +00:00
b5a65b9d10
[claude] Add unit tests for health.py ( #945 ) ( #1002 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:10:53 +00:00
43030b7db2
[claude] DRY up tasks_pending/active/completed in tasks.py ( #942 ) ( #1020 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:10:05 +00:00
ab36149fa5
[claude] Auto-create Gitea issues from research findings ( #977 ) ( #1060 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:09:18 +00:00
6a674bf9e0
[claude] Set up MCP bridge for Qwen3 via Ollama ( #1067 ) ( #1081 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:09:11 +00:00
df7358b383
[claude] Extract hardcoded sats limit in consult_grok() ( #937 ) ( #1058 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 15:07:40 +00:00
af0963a8c7
[loop-cycle-1] refactor: break up run_agentic_loop ( #531 ) ( #1084 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 15:06:59 +00:00
dd65586b5e
[claude] Execute deep backlog triage — harness vs infrastructure separation ( #1076 ) ( #1082 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Claude (Opus 4.6) <claude@hermes.local >
Co-committed-by: Claude (Opus 4.6) <claude@hermes.local >
2026-03-23 14:59:09 +00:00
7f875398fc
[claude] Add sovereignty metrics tracking + dashboard panel ( #981 ) ( #1083 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 14:09:03 +00:00
fc53a33361
[claude] Enforce coverage threshold in CI workflow ( #935 ) ( #1061 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 02:19:26 +00:00
1697e55cdb
[claude] Add content moderation pipeline (Llama Guard + game-context prompts) ( #1056 ) ( #1059 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 02:14:42 +00:00
092c982341
[claude] Ingest integration architecture research and triage work ( #946 ) ( #1057 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-23 01:40:39 +00:00
45bde4df58
[claude] Add agent performance regression benchmark suite ( #1015 ) ( #1053 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 23:55:27 +00:00
c0f6ca9fc2
[claude] Add web_fetch tool (trafilatura) for full-page content extraction ( #973 ) ( #1004 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Tests / lint (pull_request) Successful in 19s
Tests / test (pull_request) Failing after 25m3s
2026-03-22 23:03:38 +00:00
9656a5e0d0
[claude] Add connection leak and pragma unit tests for db_pool.py ( #944 ) ( #1001 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 22:56:58 +00:00
Alexander Whitestone
e35a23cefa
[claude] Add research prompt template library ( #974 ) ( #999 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Alexander Whitestone <alexpaynex@gmail.com >
Co-committed-by: Alexander Whitestone <alexpaynex@gmail.com >
2026-03-22 22:44:02 +00:00
Alexander Whitestone
3ab180b8a7
[claude] Add Gitea backup script ( #990 ) ( #996 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Alexander Whitestone <alexpaynex@gmail.com >
Co-committed-by: Alexander Whitestone <alexpaynex@gmail.com >
2026-03-22 22:36:51 +00:00
e24f49e58d
[kimi] Add JSON validation guard to queue.json writes ( #952 ) ( #995 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 22:33:40 +00:00
1fa5cff5dc
[kimi] Fix GITEA_API configuration in triage scripts ( #951 ) ( #994 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 22:28:23 +00:00
e255e7eb2a
[kimi] Add docstrings to system.py route handlers ( #940 ) ( #992 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 22:12:36 +00:00
c3b6eb71c0
[kimi] Add docstrings to src/dashboard/routes/tasks.py ( #939 ) ( #991 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 22:08:28 +00:00
bebbe442b4
feat: WorldInterface + Heartbeat v2 ( #871 , #872 ) ( #900 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Perplexity Computer <perplexity@tower.local >
Co-committed-by: Perplexity Computer <perplexity@tower.local >
2026-03-22 13:44:49 +00:00
77a8fc8b96
[loop-cycle-5] fix: get_token() priority order — config before repo-root fallback ( #899 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 01:52:40 +00:00
a3009fa32b
fix: extract hardcoded values to config, clean up bare pass ( #776 , #778 , #782 ) ( #793 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Perplexity Computer <perplexity@tower.local >
Co-committed-by: Perplexity Computer <perplexity@tower.local >
2026-03-22 01:46:15 +00:00
447e2b18c2
[kimi] Generate daily/weekly agent scorecards ( #712 ) ( #790 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Kimi Agent <kimi@timmy.local >
Co-committed-by: Kimi Agent <kimi@timmy.local >
2026-03-22 01:41:52 +00:00
17ffd9287a
[kimi] Document Timmy Automations backlog organization ( #720 ) ( #787 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Kimi Agent <kimi@timmy.local >
Co-committed-by: Kimi Agent <kimi@timmy.local >
2026-03-22 01:41:23 +00:00
5b569af383
[loop-cycle] fix: consume cycle_result.json after reading ( #897 ) ( #898 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-22 01:38:07 +00:00
e4864b14f2
[kimi] Add Submit Job modal with client-side validation ( #754 ) ( #832 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 22:14:19 +00:00
e99b09f700
[kimi] Add About/Info panel to Matrix UI ( #755 ) ( #831 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 22:06:18 +00:00
2ab6539564
[kimi] Add ConnectionPool class with unit tests ( #769 ) ( #830 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 22:02:08 +00:00
28b8673584
[kimi] Add unit tests for voice_tts.py ( #768 ) ( #829 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 21:56:45 +00:00
2f15435fed
[kimi] Implement quick health snapshot before coding ( #710 ) ( #828 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 21:53:40 +00:00
dfe40f5fe6
[kimi] Centralize agent token rules and hooks for automations ( #711 ) ( #792 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 21:44:35 +00:00
6dd48685e7
[kimi] Weekly narrative summary generator ( #719 ) ( #791 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 21:36:40 +00:00
a95cf806c8
[kimi] Implement token quest system for agents ( #713 ) ( #789 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 20:45:35 +00:00
19367d6e41
[kimi] OpenClaw architecture and deployment research report ( #721 ) ( #788 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 20:36:23 +00:00
7e983fcdb3
[kimi] Add dashboard card for Daily Run and triage metrics ( #718 ) ( #786 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 19:58:25 +00:00
46f89d59db
[kimi] Add Golden Path generator for longer sessions ( #717 ) ( #785 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 19:41:34 +00:00
e3a0f1d2d6
[kimi] Implement Daily Run orchestration script (10-minute ritual) ( #703 ) ( #783 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 19:24:43 +00:00
2a9d21cea1
[kimi] Implement Daily Run orchestration script (10-minute ritual) ( #703 ) ( #783 )
...
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
Co-authored-by: Kimi Agent <kimi@timmy.local >
Co-committed-by: Kimi Agent <kimi@timmy.local >
2026-03-21 19:24:42 +00:00
05b87c3ac1
[kimi] Implement Timmy control panel CLI entry point ( #702 ) ( #767 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 19:15:27 +00:00
8276279775
[kimi] Create central Timmy Automations module ( #701 ) ( #766 )
Tests / lint (push) Has been cancelled
Tests / test (push) Has been cancelled
2026-03-21 19:09:38 +00:00
