AI 应用开发

1. Tutorials

   Calling an LLM with Java 8 — from one request to a conversation

   Three runnable Java demos explain HTTP requests, JSON parsing, timeouts and conversation history.

   2026-09-1215 MINPublished
2. Tutorials

   Java LLM Practice II: How to validate model JSON after HTTP 200

   Build a Java 8 output boundary from a real fenced response and three timeouts, with strict validation, a bounded format adapter and reproducible evidence.

   2026-09-2816 MINPublished
3. Engineering cases

   Java LLM practice 3: don't let a failed request change conversation history

   Candidate snapshots, complete-pair commits and a UTF-8 request budget: 41 offline checks for history that survives failed requests.

   2026-09-3010 MINPublished
4. Engineering cases

   Java LLM IV: which concurrent response may commit?

   Reproduce reversed response order with real Java threads, then enforce versioned commits, complete turns and bounded receipts.

   2026-10-038 MINPublished
5. Engineering cases

   Java LLM V: why can a timed-out tool keep running?

   Build an allowlisted read-only executor and reproduce the distinction between timeout, cancellation and termination.

   2026-10-038 MINPublished
6. Engineering cases

   Java LLM practice (8): should an interrupted stream enter conversation history?

   22 loopback HTTP cases separate incremental preview from committing history, testing UTF-8, SSE framing, cancellation and abnormal endings.

   2026-10-0311 MINPublished
7. Engineering cases

   Java LLM practice (9): why can a cancelled answer overwrite a new conversation?

   18 controlled thread schedules test request ownership for streaming previews, completion and errors, with cancellation and bounded deduplication.

   2026-10-0410 MINPublished
8. Engineering cases

   Java LLM practice (10): why is the reader still running after cancellation?

   30 local HTTP connections separate conversation invalidation, reader exit and server work, comparing Future interruption with socket closure.

   2026-10-0511 MINPublished
9. Engineering cases

   Does TypeScript validate model output? A 32-case comparison with Java

   Assertions, unknown and raw JSON: 22 false accepts, four object-validation blind spots and a bounded Java/TypeScript comparison.

   2026-09-3011 MINPublished
10. Engineering cases

    Inside AI Radar — from an RSS response to a published page

    Trace the site's actual collection windows, daily quotas, deduplication and publishing checks, then diagnose a successful run that produced no visible update.

    2026-09-2212 MINPublished
11. Engineering cases

    Java history and request windows: can a trimmed fact return?

    Follow narrowing, commit, restart and expansion to separate durable conversation history from one request context.

    2026-10-079 MINPublished
12. Engineering cases

    Java retries: three timeouts are not one deadline

    Seven local HTTP conditions separate retryability, Retry-After, attempt limits and elapsed-time budgets.

    2026-10-079 MINPublished
13. Engineering cases

    Durable Java turns: what survives a process crash?

    Checksummed append records, 142 truncated prefixes and three halted JVMs distinguish local recovery from remote exactly-once execution.

    2026-10-079 MINPublished
14. Tutorials

    Java idempotent retries: no reply does not mean no effect

    Seven loopback HTTP fault cases explain idempotency keys, concurrent admission, payload conflicts and process-crash gaps.

    2026-10-0911 MINPublished
15. Tutorials

    Durable idempotency: commit identity and result together

    Use a framed journal, process crashes and 99 truncated prefixes to explain durable idempotency.

    2026-10-1110 MINPublished
16. Tutorials

    Outbox delivery: local durability is not remote exactly-once

    Compare keyed and unkeyed receivers to separate lost replies, missing receipts and duplicate remote effects.

    2026-10-1110 MINPublished
17. Tutorials

    Conversation recovery: reconcile intent, receipt and whole turn

    Halt the JVM at three commit boundaries and rebuild whole-turn history from durable facts.

    2026-10-1110 MINPublished

An engineering subdirection of AI applications.

• AI Coding
• Codex
• MCP
• Skills
• Harness
• Testing
• Evals
• Observability
• Production
• Performance

Knowledge retrieval and answer evaluation: explore RAG →

1. PROJECT / 001

   Hohoo’s AI Lab

   A personal knowledge site for public learning, research signals and practice.

   2026-09-11Live
2. PROJECT / 002

   Java LLM Practice

   Reproducible Java conversation, retry and persistence boundaries, alongside attention, cache-cost and quantization-error experiments.

   Building