PLAN § v8.1.3 punkt 5. watch-cron.mjs started the orchestrator with
cwd = pluginRoot, so every watched project was outside cwd, i.e. not the
caller's own working tree, and its .llm-security-ignore / policy.json
were dropped: the user saw findings they had already suppressed. The
orchestrator now runs with cwd = the target dir (its parent for a file);
a relative target.path still resolves against pluginRoot as before.
The scope test's entropy blob is now fixed instead of random: one run
with a random blob reported zero findings for both projects, probably a
blob starting with `/` (skipped as a path, 1 in 64). Red on 002c0ba with
the fixed blob, verified.
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Add /ultraresearch-local for structured research combining local codebase
analysis with external knowledge via parallel agent swarms. Produces research
briefs with triangulation, confidence ratings, and source quality assessment.
New command: /ultraresearch-local with modes --quick, --local, --external, --fg.
New agents: research-orchestrator (opus), docs-researcher, community-researcher,
security-researcher, contrarian-researcher, gemini-bridge (all sonnet).
New template: research-brief-template.md.
Integration: --research flag in /ultraplan-local accepts pre-built research
briefs (up to 3), enriches the interview and exploration phases. Planning
orchestrator cross-references brief findings during synthesis.
Design principle: Context Engineering — right information to right agent at
right time. Research briefs are structured artifacts in the pipeline:
ultraresearch → brief → ultraplan --research → plan → ultraexecute.
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>