9 Commits

Author	SHA1	Message	Date
Christian Gunderman	600ff5d316	fix(bot): add anti-hallucination rule to prompts	2026-05-15 11:24:23 -07:00
Christian Gunderman	ad612d9311	chore(bot): strengthen mandate execution and skill activation instructions	2026-05-14 12:03:27 -07:00
Christian Gunderman	6efdbd3e48	fix(bot): improve reasoning resilience and prevent infinite loops ... - Update PR skill to allow informed escalation and help requests when stuck. - Update main brain prompt to encourage strategic pivoting between hypotheses. - Explicitly authorize bailing out of tasks that cannot be verified.	2026-05-13 21:50:51 -07:00
Christian Gunderman	a2841350ba	fix(bot): implement prompt-level loop prevention and enforce test timeouts	2026-05-13 21:15:05 -07:00
Christian Gunderman	c460745bcb	fix(bot): enforce github-first discovery and forbid local fishing ... - Updates the `issue-fixer` skill to strictly forbid the use of local tools (like lint, tsc, grep) for finding tasks. - Updates `scheduled.md` to clarify that local tools are for verification only.	2026-05-13 10:12:43 -07:00
Christian Gunderman	278858ed11	fix(bot): satisfy YAML lint rules and clarify monorepo build order	2026-05-13 09:54:50 -07:00
Christian Gunderman	e9df8d2914	fix(bot): allow redirection in CI policy and improve skill activation steering	2026-05-12 22:20:37 -07:00
Christian Gunderman	c1b15d23b6	fix(ci): make scheduled brain base prompt generic to respect mandate	2026-05-12 14:55:53 -07:00
Christian Gunderman	2334e9b1c4	Incremental refactor repo agent towards skills-based composition (#26717) ... Co-authored-by: gemini-code-assist[bot] <176961590+gemini-code-assist[bot]@users.noreply.github.com>	2026-05-12 20:37:09 +00:00