feat(research): add research module with backend, UI, and DB integration

[dakshmhatre434-ops]

Thinking Path

• Paperclip orchestrates AI agents for zero-human companies
• The Research subsystem enables deep, multi-step research tasks powered by LLMs
• Currently, Paperclip lacks a dedicated research module for long-running, iterative research workflows
• Users need a way to create research sessions, track progress, view findings/sources, and manage memory
• This pull request adds a full-stack research module: DB schema, backend services, REST API, and React UI
• The benefit is users can now run structured research sessions with lifecycle states, progress tracking, and editable findings

What Changed

• Added 5 new DB tables: research_sessions, research_tasks, research_findings, research_sources, research_memory with 6 migrations (0091-0097)
• Added shared types, constants, and validators for the research domain in packages/shared
• Added backend services: research-llm.ts, research-progress.ts, research-search.ts for LLM-driven research orchestration
• Added REST API routes for research session CRUD, progress, findings, sources, and memory
• Added React UI components: CreateSessionDialog, ResearchFindingsList, ResearchMemoryView, ResearchSourcesList, ResearchDashboard, ResearchSessionDetail
• Added AgentAnalytics page for agent performance metrics
• Updated App.tsx, Sidebar, and routing to include research navigation
• Added agent-executor.ts route for agent execution hooks

Verification

pnpm -r typecheck
pnpm test:run
pnpm build

• Start dev server (pnpm dev) and navigate to /research to create a session
• Verify session lifecycle: pending -> running -> completed/failed/cancelled
• Check findings, sources, and memory populate correctly in the detail view

Risks

• Database migrations are additive but touch the migration journal; verify on a staging DB before production
• New UI routes may conflict with existing navigation if branch is stale -- rebase if needed
• LLM research services depend on external search APIs; failures are handled gracefully but may degrade UX
• Low risk of breaking existing features since this is an additive module

For core feature work, check ROADMAP.md first and discuss it in #dev before opening the PR. Feature PRs that overlap with planned core work may need to be redirected -- check the roadmap first. See CONTRIBUTING.md.

Model Used

• Kimi k2.5 (Moonshot AI) -- 256K context window, tool use enabled, coding assistant mode
• Assisted with backend service logic, React component scaffolding, and DB schema design

Checklist

• I have included a thinking path that traces from project context to this change
• I have specified the model used (with version and capability details)
• I have checked ROADMAP.md and confirmed this PR does not duplicate planned core work
• I have run tests locally and they pass
• I have added or updated tests where applicable
• If this change affects the UI, I have included before/after screenshots
• I have updated relevant documentation to reflect my changes
• I have considered and documented any risks above
• I will address all Greptile and reviewer comments before requesting merge