πŸŽ‰ PrimeSkills LiveVisit β†’
⚑Solo Founder · Independent Creator

Hi, I'mDongqi Chen
Building Interesting Things Here

10+ years in automotive systems, AI application explorer, indie developer. Sharing hands-on experience in in-vehicle development, AI engineering, and team management, while incubating small but beautiful products.

CarOSAI/LLMIndie Hacker
BLOG

Latest Articles

Technical articles, tutorials, and insights covering automotive dev, AI engineering, and team management

Code AgentHarness EngineeringControl Flow

Code Agent Dissection (11): Harness Design Part 1 β€” Control Flow

Examining MyCodeAgent's control flow from a harness engineering design perspective: why a single main loop rather than multiple nested loops, the engineering value of immutable state machines, the completion gate's feedback loop design, and the completeness of termination paths. This is the first article of Part 4 Harness Engineering, focused on 'why it was designed this way' rather than 'what it is.'

Β·8 min
Code AgentContext EngineeringToken Budget

Code Agent Dissection (09): When the Conversation Gets Too Long, What Happens When Tokens Run Out?

A deep dive into MyCodeAgent's context engineering: HistoryManager's append-only fact log, ProjectionBuilder's read-time projection, ContextBudgetPolicy's trigger logic, and ContextCompactor's LLM summary compression. Understand why 'history is never deleted' and 'giving the model a bounded view' are two completely different things, and how an agent compresses context within budget without losing facts.

Β·8 min
Code AgentTranscriptPersistence

Code Agent Dissection (10): When the Agent Crashes, How Does It Recover? Where Is Conversation History Stored?

A deep dive into MyCodeAgent's persistence and recovery mechanism: TranscriptStore's append-only JSONL event stream, five event types, ResumeLoader rebuilding runtime state from events, UncertainAction's tool interruption handling, and SessionMemory for cross-run feed-forward memory. Understand why agents can't rely on memory for history, and the complete chain for deterministic crash recovery.

Β·9 min
enterprise knowledge baseGraphRAGHippoRAG

Enterprise Knowledge Base (03): Graph-Enhanced RAG Benchmark β€” GraphRAG vs HippoRAG

Same 89 questions, two graph-enhanced RAG frameworks: GraphRAG 3.1.1 and HippoRAG 2.0. This article covers the full deployment journey β€” GLM-4-flash structured output failures, LanceDB dimension mismatches, NV-Embed-v2 offline loading β€” and the actual numbers across single-hop, multi-hop, and boundary refusal.

Β·9 min
Code AgentSubagentTask Tool

Code Agent Dissection (08): When a Task Is Too Complex, How Do You Delegate to a Sub-Agent?

A deep dive into MyCodeAgent's sub-agent mechanism: the Task tool, RuntimeProfile sandbox constraints, SubagentLauncher's complete execution chain, and structured result contracts. Understand how the main agent delegates exploratory tasks to a read-only lightweight sub-agent, and why sub-agents are not 'simplified main agents' but strictly constrained execution units.

Β·13 min
Code AgentMCPTool Adapter

Code Agent Dissection (07): How Are External Tools Integrated? A Deep Dive into MCP

A deep dive into MyCodeAgent's MCP integration: optional dependencies, config discovery, stdio/HTTP transport, Adapter disguising remote tools as local Tools, and result normalization into a unified protocol. Understand how external capabilities enter the same tool pipeline, and why 'registered in the registry' and 'allowed to execute' are two separate concerns.

Β·11 min
PRODUCTS

Things I've Built

Independent products, from idea to launch β€” all by myself

PODCAST

Let's Talk

Sharing tech insights and life thoughts on podcasts

CONNECT

Find Me

Follow me on these platforms for the latest updates

βœ‰οΈ

Subscribe to Newsletter

Curated content delivered to your inbox weekly β€” tech insights, product updates, and industry trends. No spam, unsubscribe anytime.

We only collect your email for the newsletter and will never share it with third parties. Unsubscribe anytime.

1,024 subscribers Β· Privacy-first, never shared