vrr/WFGY
2
0
Fork 0
mirror of https://github.com/onestardao/WFGY.git synced 2026-04-26 10:40:55 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4
WFGY/ProblemMap/GlobalFixMap/DevTools_CodeAI/jetbrains_ai_assistant.md

11 KiB
Raw Blame History

JetBrains AI Assistant: Guardrails and Fix Patterns

🧭 Quick Return to Map

You are in a sub-page of DevTools_CodeAI.
To reorient, go back here:

Think of this page as a desk within a ward.
If you need the full triage and all prescriptions, return to the Emergency Room lobby.

A practical guide to stabilize AI Assistant inside IntelliJ IDEA, PyCharm, WebStorm, Rider and friends. Targets mixed contexts like multi module Gradle or Maven projects, test generation, refactors, and doc lookups. Use this to localize the failing layer, then jump to the exact WFGY fix page with measurable acceptance.

Open these first

Core acceptance

  • ΔS(question, retrieved) ≤ 0.45
  • Coverage ≥ 0.70 to the target file or spec anchor
  • λ remains convergent across three paraphrases and two seeds
  • E_resonance stays flat across long edit plans

Fix in 60 seconds

  1. Measure ΔS Compute ΔS(question, retrieved) and ΔS(retrieved, expected anchor). Stable less than 0.40. Transitional 0.40 to 0.60. Risk is 0.60 or above.

  2. Probe λ_observe Switch between IDE code search and embedding context. Vary k as 5, 10, 20. Pin rerankers. If ΔS stays high and flat, suspect metric or index mismatch. If λ flips on harmless header reorder, lock the schema and clamp with BBAM.

  3. Apply the module

  • Retrieval drift in code or doc lookup → BBMC plus Data Contracts
  • Reasoning collapse in multi step refactors → BBCR bridge plus BBAM, verify with Logic Collapse
  • Dead ends in long edit plans or test generation → BBPF alternate paths
  • Hybrid search worse than single → Pattern Query Parsing Split and Rerankers

Typical JetBrains breakpoints and the right fix

  • Multi module Gradle or Maven skew Context pulls from sibling modules or stale targets. Lock anchors with module_path, pom.xml or build.gradle hash, and sourceSet. Warm the index after sync. Open: Retrieval Traceability, Bootstrap Ordering

  • Wrong symbol in a monorepo Embeddings prefer near neighbors. Require cite then explain with exact spans. Open: Embedding ≠ Semantic, Data Contracts

  • Generated tests reference phantom helpers Enforce file anchors and commit SHA before test generation. Open: Data Contracts

  • Long chat drift during refactors and inspections Plan degrades after 25 to 40 steps. Split the plan and re join with a BBCR bridge. Open: Context Drift, Entropy Collapse

  • Index readiness and language server mismatch First run fails or cites wrong files. Add warm up fences and verify analyzer versions. Open: Bootstrap Ordering

  • Unsafe shell or Gradle tasks suggested from README Lock tool allow lists and apply SCU separation for untrusted text. Open: Prompt Injection, Pattern: SCU

IDE checklist for JetBrains AI Assistant

  • Warm up the selected context source and confirm INDEX_HASH, LANG_SERVER_VER, and project model synced.
  • Use one retrieval metric per run. Do not mix analyzers while fixing a single bug.
  • Prompts carry anchors: repo@commit, module_path, file_path, symbol, line_start, line_end, snippet_id.
  • Log per step: ΔS, λ state, coverage. Alert when ΔS ≥ 0.60 or λ diverges.
  • Regression gate requires tests pass, coverage ≥ 0.70, ΔS ≤ 0.45, identical diff twice.

Minimal schema you should capture

{ repo, commit_sha, module_path, file_path, symbol, line_start, line_end, snippet_id, tokens, ΔS, λ_state } Require cite then explain. Forbid cross module reuse without a new citation.

Deep diagnostics

  • Three paraphrase probe Ask the same change three ways. If λ flips on harmless header reorder, clamp with BBAM and lock the schema.

  • Anchor triangulation Compare ΔS for target vs a decoy module or sibling package. If close, re chunk and normalize embeddings. See: Retrieval Playbook, Embedding ≠ Semantic

  • Plan length audit If entropy rises after 25 to 40 steps, split the plan and re join with a BBCR bridge. See: Entropy Collapse

  • Live instability Add probes and backoff guards in Run Configurations or task runners. See: Live Monitoring for RAG, Debug Playbook

Copy paste prompt for JetBrains AI chat

You have TXTOS and the WFGY Problem Map loaded.

My JetBrains AI issue:
- symptom: [one line]
- anchors: repo={name}, commit={sha}, module={path}, file={path}, lines={a..b}
- traces: ΔS(question,retrieved)=..., ΔS(retrieved,anchor)=..., λ across 3 paraphrases

Tell me:
1) the failing layer and why,
2) the exact WFGY page to open,
3) minimal steps to push ΔS ≤ 0.45 and keep λ convergent,
4) a reproducible test to verify the fix.
Use BBMC, BBPF, BBCR, BBAM when relevant. Keep it auditable and short.

🔗 Quick-Start Downloads (60 sec)

Tool Link 3-Step Setup
WFGY 1.0 PDF Engine Paper 1️⃣ Download · 2️⃣ Upload to your LLM · 3️⃣ Ask “Answer using WFGY + <your question>”
TXT OS (plain-text OS) TXTOS.txt 1️⃣ Download · 2️⃣ Paste into any LLM chat · 3️⃣ Type “hello world” — OS boots instantly

Explore More

Layer Page What it’s for
⭐ Proof WFGY Recognition Map External citations, integrations, and ecosystem proof
⚙️ Engine WFGY 1.0 Original PDF tension engine and early logic sketch (legacy reference)
⚙️ Engine WFGY 2.0 Production tension kernel for RAG and agent systems
⚙️ Engine WFGY 3.0 TXT based Singularity tension engine (131 S class set)
🗺️ Map Problem Map 1.0 Flagship 16 problem RAG failure taxonomy and fix map
🗺️ Map Problem Map 2.0 Global Debug Card for RAG and agent pipeline diagnosis
🗺️ Map Problem Map 3.0 Global AI troubleshooting atlas and failure pattern map
🧰 App TXT OS .txt semantic OS with fast bootstrap
🧰 App Blah Blah Blah Abstract and paradox Q&A built on TXT OS
🧰 App Blur Blur Blur Text to image generation with semantic control
🏡 Onboarding Starter Village Guided entry point for new users

If this repository helped, starring it improves discovery so more builders can find the docs and tools.
GitHub Repo stars