serversdown 1dea65794b fix: record_hand recovers when the model uses log_hand's field schema ...

Live-session bug: the chat model called record_hand but filled log_hand's
granular fields (position/hole_cards/board/streets), leaving `shorthand` empty →
the parser got nothing → "I couldn't parse that hand". The fragment/tool choice
was correct; only the argument shape was wrong.

- _record_hand now reconstructs a parseable description from the granular fields
  when `shorthand` is empty (_shorthand_from_fields), so it works regardless of
  which schema the model uses. Explicit `shorthand` still passes verbatim.
- Sharpened record_hand's spec: pass the ENTIRE hand as ONE `shorthand` string,
  not split fields (that's log_hand); shorthand is required + non-empty.

4 tests. Full suite 210 green.

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

2026-07-07 16:05:31 +00:00

..

test_chat.py

perf: tighten the dynamic prompt — persona split + lean deliberation

2026-06-24 20:48:44 +00:00

test_cognition.py

feat: associative cognition — thoughts arise from spreading activation, not a re-read bio

2026-06-22 05:45:39 +00:00

test_dream.py

feat: cloud-first consolidation routing + graceful backend fallback

2026-07-07 06:53:55 +00:00

test_equity.py

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

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

test_era.py

perf: incremental era rebuilds — skip unchanged months

2026-06-25 03:31:02 +00:00

test_hand_schema.py

fix: don't attribute observed hands to the hero

2026-07-04 02:58:02 +00:00

test_hand_tools.py

fix: record_hand recovers when the model uses log_hand's field schema

2026-07-07 16:05:31 +00:00

test_llm_bounds.py

feat: cloud-first consolidation routing + graceful backend fallback

2026-07-07 06:53:55 +00:00

test_modes.py

feat: she can suggest + switch modes (set_mode tool + mode awareness)

2026-06-24 16:32:42 +00:00

test_pattern_recall.py

feat: dream-cycle merge scan + pattern desk (leak recall)

2026-07-03 23:01:53 +00:00

test_perceive.py

feat(prompting): Phase B step 2 — wire the sharded poker prompt into the pipeline

2026-07-05 02:57:30 +00:00

test_poker_api.py

feat: reads/players API + REST route conformance test

2026-06-29 00:02:25 +00:00

test_poker_contract.py

feat: reads/players API + REST route conformance test

2026-06-29 00:02:25 +00:00

test_poker_prompts.py

feat(prompting): harden the poker classifier against real-world phrasings

2026-07-05 03:28:10 +00:00

test_poker.py

feat: edit hands from the viewer + "not my hand" disown

2026-07-04 03:00:21 +00:00

test_profile.py

perf: incremental profile rebuilds — fold new gists instead of re-digesting all

2026-06-25 04:05:24 +00:00

test_ratings.py

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

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

test_reflect.py

feat: cloud-first consolidation routing + graceful backend fallback

2026-07-07 06:53:55 +00:00

test_roster.py

feat: clear_table — empty the roster on a table change

2026-07-04 07:01:11 +00:00

test_scouting.py

feat: scouting desk — proactive villain recall injected before she replies

2026-07-03 22:49:40 +00:00

test_summary_fallback.py

feat: guard summaries against degenerate (garbage) backend output

2026-07-04 07:26:17 +00:00

test_thoughts.py

feat: cloud-first consolidation routing + graceful backend fallback

2026-07-07 06:53:55 +00:00

test_time.py

refactor(P1): extract the turn pipeline into lyra/mind.py (behavior-preserving)

2026-06-24 05:19:39 +00:00

test_tools.py

refactor(P1): extract the turn pipeline into lyra/mind.py (behavior-preserving)

2026-06-24 05:19:39 +00:00

test_transcript.py

feat: full-fidelity conversation export (chat + tool calls)

2026-07-03 19:22:03 +00:00

test_villain_tools.py

fix: stop spawning duplicate villains from descriptions in the name field

2026-07-04 03:16:50 +00:00

test_villains.py

feat(poker): nameless-villain identity resolution engine

2026-07-03 22:46:24 +00:00