8 KiB
DevTools · Code AI — Global Fix Map
A hub to stabilize IDE copilots and code-AI assistants without changing infra.
Use this to jump to per-tool guardrails and verify fixes with the same acceptance targets.
When to use this folder
- IDE chat answers flip between runs or tabs.
- Tool calls loop or stall after partial edits.
- JSON blocks fail or come back as prose.
- RAG answers look right by similarity yet cite the wrong place.
- Long refactors drift after 20–40 reasoning steps.
Acceptance targets
- ΔS(question, retrieved) ≤ 0.45
- Coverage of target section ≥ 0.70
- λ stays convergent across 3 paraphrases and 2 seeds
- E_resonance flat on long windows
Quick routes to per-tool pages
- GitHub Copilot: github_copilot.md
- Cursor: cursor.md
- Sourcegraph Cody: sourcegraph_cody.md
- VS Code Copilot Chat: vscode_copilot_chat.md
- Codeium: codeium.md
- Tabnine: tabnine.md
- AWS CodeWhisperer: aws_codewhisperer.md
- JetBrains AI Assistant: jetbrains_ai_assistant.md
Map symptoms → structural fixes
- Wrong-meaning hits despite high similarity
→ embedding-vs-semantic.md - Citations do not line up with the returned section
→ retrieval-traceability.md · data-contracts.md - Answers flip between sessions or file tabs
→ context-drift.md · entropy-collapse.md - JSON mode breaks or tools accept prose
→ logic-collapse.md · prompt-injection.md - Multi-agent or tool handoff stalls
→ Multi-Agent_Problems.md · role drift deep dive → multi-agent-chaos/role-drift.md - Hybrid retrievers worse than single
→ patterns/pattern_query_parsing_split.md · rerankers.md
Fix in 60 seconds
-
Measure ΔS
Compute ΔS(question, retrieved) and ΔS(retrieved, expected anchor).
Stable < 0.40, transitional 0.40–0.60, risk ≥ 0.60. -
Probe λ_observe
Vary k and headers. If λ flips, lock schema and apply BBAM variance clamp. -
Apply modules
Retrieval drift → BBMC + data-contracts.md
Reasoning collapse → BBCR bridge + BBAM + logic-collapse.md
Long-run dead ends → BBPF alternate paths -
Verify
Coverage ≥ 0.70 on 3 paraphrases. λ convergent on 2 seeds.
Copy-paste prompt for IDE chat
I loaded TXT OS and the WFGY Problem Map.
My code-AI issue:
* symptom: \[one line]
* traces: ΔS(question,retrieved)=..., ΔS(retrieved,anchor)=..., λ states across 3 paraphrases
Tell me:
1. failing layer and why,
2. the exact WFGY page to open from this repo,
3. minimal steps to push ΔS ≤ 0.45 and keep λ convergent,
4. how to verify with a reproducible test.
Use BBMC/BBPF/BBCR/BBAM where relevant.
🔗 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
| Module | Description | Link |
|---|---|---|
| WFGY Core | WFGY 2.0 engine is live: full symbolic reasoning architecture and math stack | View → |
| Problem Map 1.0 | Initial 16-mode diagnostic and symbolic fix framework | View → |
| Problem Map 2.0 | RAG-focused failure tree, modular fixes, and pipelines | View → |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | View → |
| Semantic Blueprint | Layer-based symbolic reasoning & semantic modulations | View → |
| Benchmark vs GPT-5 | Stress test GPT-5 with full WFGY reasoning suite | View → |
| 🧙♂️ Starter Village 🏡 | New here? Lost in symbols? Click here and let the wizard guide you through | Start → |
👑 Early Stargazers: See the Hall of Fame —
⭐ WFGY Engine 2.0 is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the Unlock Board.
