Logo
Explore Help
Register Sign In
sorokin.oleg.edu/learnharness
Watch 1
Star 0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 6 Wiki Activity
Files
a3aabb3a57a27c815fdf31bb927d29b6ec2ed4fc
learnharness/src/agent
T
History
amosblomqvist a3aabb3a57 extractor redesign: chains are the deliverable (owner-approved, goal-first)
2026-09-30 02:09:25 +03:00
..
prompts
explain refinements: no opt-out row, one committed field (owner 2026-09-27)
2026-09-27 09:13:34 +03:00
subagents
extractor redesign: chains are the deliverable (owner-approved, goal-first)
2026-09-30 02:09:25 +03:00
tools
auditor grounding — a prescribed, bounded exploration procedure + born-in find pointers
2026-09-29 04:10:38 +03:00
models.ts
feat(models): clamp-on-write for pinned thinking levels + DEFAULT_THINKING_ORDER in the core barrel
2026-09-22 21:44:43 +03:00
prompt-segments.ts
de-meta the system prompts; method leads the composition (owner, 2026-09-27)
2026-09-27 04:14:42 +03:00
system-prompt.md
de-meta the system prompts; method leads the composition (owner, 2026-09-27)
2026-09-27 04:14:42 +03:00
teacher-agent.ts
free-recall explain tool: the quizzing-mechanic switch (owner 2026-09-27)
2026-09-27 08:55:13 +03:00
tool-execute.ts
Wave A: pi-native tool layer — delete LhTool/toPiTool, TypeBox everywhere, terminate on questions
2026-09-25 23:32:13 +03:00
tools.ts
explain refinements: no opt-out row, one committed field (owner 2026-09-27)
2026-09-27 09:13:34 +03:00
Powered by Gitea Version: 1.27.3 Page: 85ms Template: 8ms
Auto
English
Bahasa Indonesia Deutsch English Español Français Gaeilge Italiano Latviešu Magyar nyelv Nederlands Polski Português de Portugal Português do Brasil Suomi Svenska Türkçe Čeština Ελληνικά Български Русский Українська فارسی മലയാളം 日本語 简体中文 繁體中文(台灣) 繁體中文(香港) 한국어
Licenses API