context（context 搜索）

[IMPORTANT] Use TaskCreate to break ALL work into small tasks BEFORE starting — including tasks for each file read. This prevents context loss from long files. For simple tasks, AI MUST ATTENTION ask user whether to skip.

Critical Thinking Mindset — Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence >80% to act. Anti-hallucination: Never present guess as fact — cite sources for every claim, admit uncertainty freely, self-check output for errors, cross-reference independently, stay skeptical of own confidence — certainty without evidence root of all hallucination.

AI Mistake Prevention — Failure modes to avoid on every task: - Check downstream references before deleting. Deleting components causes documentation and code staleness cascades. Map all referencing files before removal. - Verify AI-generated content against actual code. AI hallucinates APIs, class names, and method signatures. Always grep to confirm existence before documenting or referencing. - Trace full dependency chain after edits. Changing a definition misses downstream variables and consumers derived from it. Always trace the full chain. - Trace ALL code paths when verifying correctness. Confirming code exists is not confirming it executes. Always trace early exits, error branches, and conditional skips — not just happy path. - When debugging, ask "whose responsibility?" before fixing. Trace whether bug is in caller (wrong data) or callee (wrong handling). Fix at responsible layer — never patch symptom site. - Assume existing values are intentional — ask WHY before changing. Before changing any constant, limit, flag, or pattern: read comments, check git blame, examine surrounding code. - Verify ALL affected outputs, not just the first. Changes touching multiple stacks require verifying EVERY output. One green check is not all green checks. - Holistic-first debugging — resist nearest-attention trap. When investigating any failure, list EVERY precondition first (config, env vars, DB names, endpoints, DI registrations, data preconditions), then verify each against evidence before forming any code-layer hypothesis. - Surgical changes — apply the diff test. Bug fix: every changed line must trace directly to the bug. Don't restyle or improve adjacent code. Enhancement task: implement improvements AND announce them explicitly. - Surface ambiguity before coding — don't pick silently. If request has multiple interpretations, present each with effort estimate and ask. Never assume all-records, file-based, or more complex path.

Quick Summary

Goal: Load project context for the current session (git status, branch info, recent changes).

Workflow:

1. Gather -- Run git status, branch info, recent commits
2. Analyze -- Identify current work context and pending changes
3. Present -- Summarize context for session awareness

Key Rules:

• Provides situational awareness at session start
• Shows branch, uncommitted changes, recent commits
• Non-destructive: read-only operation

Be skeptical. Apply critical thinking, sequential thinking. Every claim needs traced proof, confidence percentages (Idea should be more than 80%).

Load Project Context

Load current development context to help with subsequent tasks.

Git Status

git status --short
git branch --show-current

Recent Activity

# Recent commits
git log --oneline -5

# Uncommitted changes
git diff --stat

Project Pattern Discovery

Read docs/project-config.json for project-specific module paths. Check modules[] for service/app list, or fall back to backendServices.serviceMap / frontendApps.appMap in older configs. If file not found, discover structure dynamically:

# Find backend service directories
find src/ -name "*.csproj" -maxdepth 4 | head -20

# Find frontend app directories
find src/ -name "package.json" -maxdepth 3 | head -10

# Find shared libraries
find . -path "*/libs/*" -name "package.json" -maxdepth 4 | head -10

Development Patterns

Backend: Clean Architecture + CQRS + Entity Events Frontend: Component framework + state management

Current Session Focus

Based on the git status, identify:

• What files are being worked on
• What feature/fix is in progress
• Any uncommitted changes that need attention

Summarize the current state to help with subsequent tasks.

Closing Reminders

• MANDATORY IMPORTANT MUST ATTENTION break work into small todo tasks using TaskCreate BEFORE starting
• MANDATORY IMPORTANT MUST ATTENTION search codebase for 3+ similar patterns before creating new code
• MANDATORY IMPORTANT MUST ATTENTION cite file:line evidence for every claim (confidence >80% to act)
• MANDATORY IMPORTANT MUST ATTENTION add a final review todo task to verify work quality
• MUST ATTENTION apply critical thinking — every claim needs traced proof, confidence >80% to act. Anti-hallucination: never present guess as fact.
• MUST ATTENTION apply AI mistake prevention — holistic-first debugging, fix at responsible layer, surface ambiguity before coding, re-read files after compaction.

[TASK-PLANNING] Before acting, analyze task scope and systematically break it into small todo tasks and sub-tasks using TaskCreate.