2 Commits

Author	SHA1	Message	Date
Claude	96c9f1b02f	fix: address audit low-hanging fruit — docs accuracy, auction timing, stubs, tests ... - Docs: "No Cloud" → "No Cloud AI" (frontend uses CDN for Bootstrap/HTMX/fonts) - Docs: "600+" → "640+" tests, "20+" → "58" endpoints (actual counts) - Docs: LND described as "scaffolded" not "gRPC-ready"; remove "agents earn sats" - Fix auction timing: coordinator sleep(0) → sleep(AUCTION_DURATION_SECONDS) - agent_core: implement remember() with dedup/eviction, communicate() via swarm comms - Tests: add CLI tests for chat, think, and backend/model-size forwarding (647 passing) https://claude.ai/code/session_01SZTwAkTg6v4ybv8g9NLxqN	2026-02-24 18:29:21 +00:00
Claude	982c42ba45	Use TIMMY_STATUS_PROMPT in CLI status command ... TIMMY_STATUS_PROMPT was defined in timmy/prompts.py and covered by tests, but never wired into the application. The CLI status command was passing a hardcoded inline string instead. Replace the inline string with the canonical prompt and add two CLI tests that verify the correct prompt is used. https://claude.ai/code/session_01DMjQ5qMZ8iHeyix1j3GS7c	2026-02-21 16:17:55 +00:00