serversdown 4f770f2e43 feat: behind-the-scenes 👍/👎 rating system (fine-tune data collection) ...

Brian can rate Lyra's outputs as he uses her; each rating is stored as a
(context, content, rating) triple — the shape a future fine-tune / preference
dataset wants, collected passively during real use.

- memory: ratings table + add_rating (upsert: one row per item, re-rating
  replaces), list_ratings, rating_counts
- server: POST /rate, GET /ratings/counts, GET /ratings/export (JSONL download)
- chat UI: subtle 👍/👎 on each assistant reply, captures the prompting message
  as context
- journal/reflection UI: 👍/👎 on each thought
- tests: counts + upsert-replace behavior

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

2026-06-18 19:32:27 +00:00

..

personas

feat: deterministic equity/board-reading tool (math via tools, not LLM)

2026-06-18 18:45:40 +00:00

web

feat: behind-the-scenes 👍/👎 rating system (fine-tune data collection)

2026-06-18 19:32:27 +00:00

__init__.py

chore: project scaffold (uv, .env.example, README, lyra package)

2026-05-16 06:01:08 +00:00

__main__.py

feat: persona chat loop, web UI, and local (Ollama) embeddings

2026-06-15 18:36:31 +00:00

backfill.py

fix: backfill skips hand extraction by default (prose->replay too lossy)

2026-06-18 06:04:02 +00:00

chat.py

feat(web): cloud chat-model selector in Settings

2026-06-18 18:55:45 +00:00

clock.py

feat: time awareness — Lyra perceives 'now' and how long it's been

2026-06-17 02:31:40 +00:00

config.py

feat: separate CHAT_MODEL (gpt-4o) for persona fidelity

2026-06-16 21:05:47 +00:00

dream.py

feat: Lyra's journal — permanent thought record + a knowing journal note

2026-06-17 06:40:46 +00:00

equity.py

feat: deterministic equity/board-reading tool (math via tools, not LLM)

2026-06-18 18:45:40 +00:00

era.py

feat: era-rollup + narrative engine (consolidation steps 3-4)

2026-06-16 19:28:01 +00:00

ingest.py

feat: import raw ChatGPT export (new sharded format)

2026-06-16 02:40:32 +00:00

llm.py

feat: tool use — Lyra's first real actions (journal_write, note)

2026-06-17 19:04:34 +00:00

logbus.py

feat: run dream cycle as a systemd user service + journald-visible logs

2026-06-17 01:42:55 +00:00

memory.py

feat: behind-the-scenes 👍/👎 rating system (fine-tune data collection)

2026-06-18 19:32:27 +00:00

narrative.py

feat: era-rollup + narrative engine (consolidation steps 3-4)

2026-06-16 19:28:01 +00:00

persona.py

feat: persona chat loop, web UI, and local (Ollama) embeddings

2026-06-15 18:36:31 +00:00

poker.py

feat: backfill poker tracker from curated .md session logs

2026-06-18 05:55:22 +00:00

profile.py

feat: profile layer — semantic memory (consolidation step 2)

2026-06-16 04:11:19 +00:00

self_state.py

feat: break reflection repetition — varied grist, show-and-forbid, wider lens

2026-06-18 19:21:51 +00:00

session.py

feat: persona chat loop, web UI, and local (Ollama) embeddings

2026-06-15 18:36:31 +00:00

summary.py

perf: concurrent summarize-all (parallel LLM, serial DB)

2026-06-16 16:30:07 +00:00

tools.py

feat: deterministic equity/board-reading tool (math via tools, not LLM)

2026-06-18 18:45:40 +00:00