perplexity/Timmy-time-dashboard
Archived
1
0
Fork 0
forked from Rockachopa/Timmy-time-dashboard
Code Issues Pull Requests 1 Activity
525 Commits 40 Branches 1 Tag
a751be3038c1586bc8f7b98f7510fa54a42548ef
Commit Graph

167 Commits

Author SHA1 Message Date
Timmy Time
92594ea588 [loop-cycle] feat: implement source distinction in system prompts (#463) (#464) 2026-03-19 14:49:31 -04:00
Kimi Agent
3590c1689e fix: make _get_loop_agent singleton thread-safe (#449) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 14:18:27 -04:00
Kimi Agent
3afb62afb7 fix: add self_reflect tool for past behavior review (#417) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 09:39:14 -04:00
Kimi Agent
332fa373b8 fix: wire cognitive state to sensory bus (presence loop) (#414) 
## Summary
- CognitiveTracker.update() now emits `cognitive_state_changed` events to the SensoryBus
- WorkshopHeartbeat (and other subscribers) react immediately to mood/engagement changes
- Closes the sense → memory → react loop described in the Workshop architecture
- Fire-and-forget emission — never blocks the chat response path
- Gracefully skips when no event loop is running (sync contexts/tests)

## Test plan
- [x] 3 new tests: event emission, mood change tracking, graceful skip without loop
- [x] All 1935 unit tests pass
- [x] Lint + format clean

Fixes #222

Co-authored-by: kimi <kimi@localhost>
Reviewed-on: http://localhost:3000/rockachopa/Timmy-time-dashboard/pulls/414
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 03:23:03 -04:00
Kimi Agent
9b8ad3629a fix: wire Pip familiar into Workshop state pipeline (#412) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 03:09:22 -04:00
Kimi Agent
4b617cfcd0 fix: deep focus mode — single-problem context for Timmy (#409) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 02:54:19 -04:00
Kimi Agent
3571d528ad feat: Workshop Phase 1 — State Schema v1 (#404) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 02:24:13 -04:00
Kimi Agent
858264be0d fix: deprecate ~/.tower/timmy-state.txt — consolidate on presence.json (#388) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 01:18:52 -04:00
Kimi Agent
da43421d4e feat: broadcast Timmy state changes via WS relay (#380) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-19 00:25:11 -04:00
Kimi Agent
864be20dde feat: Workshop state heartbeat for presence.json (#377) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 22:07:32 -04:00
Kimi Agent
c1f939ef22 fix: add update_gitea_avatar capability (#368) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 22:04:57 -04:00
hermes
c1af9e3905 [loop-cycle-154] refactor: extract _annotate_confidence helper — DRY 3x duplication (#369) (#376) 2026-03-18 22:01:51 -04:00
Kimi Agent
996ccec170 feat: Pip the Familiar — behavioral state machine (#367) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 21:50:36 -04:00
Kimi Agent
560aed78c3 fix: add cognitive state as observable signal for Matrix avatar (#358) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 21:37:17 -04:00
hermes
ce658c841a [loop-cycle-151] refactor: extract embedding functions to memory/embeddings.py (#344) (#355) 2026-03-18 21:24:50 -04:00
Kimi Agent
243b1a656f feat: give Timmy hands — artifact tools for conversation (#337) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 20:36:38 -04:00
hermes
22e0d2d4b3 [loop-cycle-66] fix: replace language-model with inference-backend in error messages (#334) 2026-03-18 20:27:06 -04:00
hermes
bcc7b068a4 [loop-cycle-66] fix: remove language-model self-reference and add anti-assistant-speak guidance (#323) (#333) 2026-03-18 20:21:03 -04:00
hermes
844923b16b [loop-cycle-65] fix: validate file paths before filing thinking-engine issues (#327) (#329) 2026-03-18 20:07:19 -04:00
Kimi Agent
8ef0ad1778 fix: pause thought counter during idle periods (#319) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 19:12:14 -04:00
Kimi Agent
9a21a4b0ff feat: SensoryEvent model + SensoryBus dispatcher (#318) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 19:02:12 -04:00
Kimi Agent
ab71c71036 feat: time adapter — circadian awareness for Timmy (#315) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 18:47:09 -04:00
Kimi Agent
39939270b7 fix: Gitea webhook adapter — normalize events to sensory bus (#309) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 18:37:01 -04:00
Kimi Agent
0ab1ee9378 fix: proactive memory status check during thought tracking (#313) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 18:36:59 -04:00
Kimi Agent
234187c091 fix: add periodic memory status checks during thought tracking (#311) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-18 18:26:53 -04:00
Kimi Agent
f5a570c56d fix: add real-time data disclaimer to welcome message (#304) 2026-03-18 16:56:21 -04:00
rockachopa
96e7961a0e fix: make confidence visible to users when below 0.7 threshold (#259) 
Co-authored-by: rockachopa <alexpaynex@gmail.com>
Co-committed-by: rockachopa <alexpaynex@gmail.com>
 2026-03-15 19:36:52 -04:00
Kimi Agent
bcbdc7d7cb feat: add thought_search tool for querying Timmy's thinking history (#260) 
Co-authored-by: Kimi Agent <kimi@timmy.local>
Co-committed-by: Kimi Agent <kimi@timmy.local>
 2026-03-15 19:35:58 -04:00
hermes
80aba0bf6d [loop-cycle-63] feat: session_history tool — Timmy searches past conversations (#251) (#258) 2026-03-15 15:11:43 -04:00
hermes
dd34dc064f [loop-cycle-62] fix: MEMORY.md corruption and hot memory staleness (#252) (#256) 2026-03-15 15:01:19 -04:00
hermes
7bc355eed6 [loop-cycle-61] fix: strip think tags and harden fact parsing (#237) (#254) 2026-03-15 14:50:09 -04:00
hermes
f9911c002c [loop-cycle-60] fix: retry with backoff on Ollama GPU contention (#70) (#238) 2026-03-15 14:28:47 -04:00
hermes
7f656fcf22 [loop-cycle-59] feat: gematria computation tool (#234) (#235) 2026-03-15 14:14:38 -04:00
hermes
8c63dabd9d [loop-cycle-57] fix: wire confidence estimation into chat flow (#231) (#232) 2026-03-15 13:58:35 -04:00
hermes
a50af74ea2 [loop-cycle-56] fix: resolve 5 lint errors on main (#203) (#224) 2026-03-15 13:40:40 -04:00
hermes
b4cb3e9975 [loop-cycle-54] refactor: consolidate three memory stores into single table (#37) (#223) 2026-03-15 13:33:24 -04:00
hermes
4a68f6cb8b [loop-cycle-53] refactor: break circular imports between packages (#164) (#193) 2026-03-15 12:52:18 -04:00
hermes
b3840238cb [loop-cycle-52] feat: response audit trail with inputs, confidence, errors (#144) (#191) 2026-03-15 12:34:48 -04:00
hermes
96c7e6deae [loop-cycle-52] fix: remove all qwen3.5 references (#182) (#190) 2026-03-15 12:34:21 -04:00
hermes
f6d74b9f1d [loop-cycle-51] refactor: remove dead code from memory_system.py (#173) (#185) 2026-03-15 12:18:11 -04:00
hermes
5b57bf3dd0 [loop-cycle-50] fix: agent retry uses exponential backoff instead of fixed 1s delay (#174) (#181) 2026-03-15 12:08:30 -04:00
hermes
bcd6d7e321 [loop-cycle-50] refactor: replace bare sqlite3.connect() with context managers batch 2 (#157) (#180) 2026-03-15 11:58:43 -04:00
hermes
bea2749158 [loop-cycle-49] refactor: narrow broad except Exception catches — batch 1 (#158) (#178) 2026-03-15 11:48:54 -04:00
hermes
204a6ed4e5 refactor: decompose _maybe_distill() into focused helpers (#151) (#160) 2026-03-15 11:23:45 -04:00
hermes
f15ad3375a [loop-cycle-47] feat: add confidence signaling module (#143) (#161) 2026-03-15 11:20:30 -04:00
hermes
5aea8be223 [loop-cycle-47] refactor: replace bare sqlite3.connect() with context managers (#148) (#155) 2026-03-15 11:05:39 -04:00
hermes
717dba9816 [loop-cycle-46] refactor: break up oversized functions in tools.py (#151) (#154) 2026-03-15 10:56:33 -04:00
hermes
466db7aed2 [loop-cycle-44] refactor: remove dead code batch 2 — agent_core + test_agent_core (#147) (#150) 2026-03-15 10:22:41 -04:00
hermes
d2c51763d0 [loop-cycle-43] refactor: remove 1035 lines of dead code (#136) (#146) 2026-03-15 10:10:12 -04:00
hermes
48c8efb2fb [loop-cycle-40] fix: use get_system_prompt() in cloud backends (#135) (#138) 
## What

Cloud backends (Grok, Claude, AirLLM) were importing SYSTEM_PROMPT directly, which is always SYSTEM_PROMPT_LITE and contains unformatted {model_name} and {session_id} placeholders.

## Changes

- backends.py: Replace `from timmy.prompts import SYSTEM_PROMPT` with `from timmy.prompts import get_system_prompt`
- AirLLM: uses `get_system_prompt(tools_enabled=False, session_id="airllm")` (LITE tier, correct)
- Grok: uses `get_system_prompt(tools_enabled=True, session_id="grok")` (FULL tier)
- Claude: uses `get_system_prompt(tools_enabled=True, session_id="claude")` (FULL tier)
- 9 new tests verify formatted model names, correct tier selection, and session_id formatting

## Tests

1508 passed, 0 failed (41 new tests this cycle)

Fixes #135

Co-authored-by: Kimi Agent <kimi@timmy.local>
Reviewed-on: http://localhost:3000/rockachopa/Timmy-time-dashboard/pulls/138
Reviewed-by: rockachopa <alexpaynex@gmail.com>
Co-authored-by: hermes <hermes@timmy.local>
Co-committed-by: hermes <hermes@timmy.local>
 2026-03-15 09:44:43 -04:00