WFGY/ProblemMap/GlobalFixMap/OpsDeploy/rollout_readiness_gate.md

Rollout Readiness Gate — OpsDeploy

A pre-ship gate that decides ship or no-ship using measurable targets.
Use this page to wire a single checkpoint in CI or CD that blocks risky changes before they hit users.

What this page is

• A compact, provider-agnostic checklist that verifies retrieval, reasoning, orchestration, and infra order.
• Direct jumps to the exact Problem Map fixes.
• Copy-paste templates you can drop into CI or a workflow runner.

When to use

• Before any production rollout that changes retrievers, embeddings, chunkers, prompts, model versions, or tool schemas.
• After index rebuilds, data migrations, or secret rotation.
• When answers recently started flipping between runs or a canary looks unstable.

Open these first

• Visual map and recovery: RAG Architecture & Recovery
• Retrieval knobs: Retrieval Playbook
• Traceability schema: Retrieval Traceability
• Snippet and citation contract: Data Contracts
• Embedding vs meaning: Embedding ≠ Semantic
• Hallucination and chunk boundaries: Hallucination
• Long chains and entropy: Context Drift, Entropy Collapse
• Logic collapse and recovery: Logic Collapse
• Prompt injection fences: Prompt Injection
• Boot order and deploy traps: Bootstrap Ordering, Deployment Deadlock, Pre-Deploy Collapse
• Live ops after ship: Live Monitoring for RAG, Debug Playbook

Acceptance targets for ship

• ΔS(question, retrieved) ≤ 0.45 on three paraphrases.
• Coverage of target section ≥ 0.70.
• λ remains convergent across two seeds.
• E_resonance stays flat on long windows.
• No schema drift in citation fields {snippet_id, section_id, source_url, offsets, tokens}.

60-second gate checklist

1. Warmup and invariants

   • Secrets present. Version lock consistent. INDEX_HASH matches retriever build.
   • Boot order ok. See Bootstrap Ordering.

2. RAG quality probe

   • Run a 20–40 item gold set.
   • Score with: RAG Precision/Recall Eval and Semantic Stability Eval.
   • Fail if any target above is missed.

3. Hallucination fence

   • Enforce cite-then-explain. Verify with Retrieval Traceability and Data Contracts.
   • Block if citations are missing or cross-section reuse appears.

4. Index and metric sanity

   • If nearest neighbors look right but meaning is wrong, rebuild. See Embedding ≠ Semantic.
   • If recall varies with HyDE or BM25, lock the two-stage query and rerank. See Query Parsing Split.
   • Fragmented stores: see Vectorstore Fragmentation.

5. Chain stability

   • If chains exceed safe length and entropy rises, split and bridge. See Context Drift and Entropy Collapse.

6. Decision

   • Ship if all targets pass on two seeds and three paraphrases.
   • Else block and open the linked fix page.

CI gate template you can paste

# opsdeploy/rollout_readiness_gate.yml
gates:
  warmup_invariants:
    checks:
      - secrets_present: true
      - index_hash_matches: true
      - version_lock: strict
      - boot_order_ok: true  # see Bootstrap Ordering
  rag_quality:
    evals:
      - name: rag_precision_recall
        spec: ProblemMap/eval/eval_rag_precision_recall.md
        min_coverage: 0.70
      - name: semantic_stability
        spec: ProblemMap/eval/eval_semantic_stability.md
        max_delta_s: 0.45
        paraphrases: 3
        seeds: 2
  hallucination_fence:
    schema: ProblemMap/data-contracts.md
    require_citations: true
  index_metric_sanity:
    actions_on_fail:
      - open: ProblemMap/embedding-vs-semantic.md
      - open: ProblemMap/patterns/pattern_query_parsing_split.md
      - open: ProblemMap/patterns/pattern_vectorstore_fragmentation.md
decision:
  on_fail: block_rollout
  on_pass: proceed_to_canary
artifacts:
  - logs/delta_s.json
  - logs/coverage.json
  - logs/lambda_states.json

Escalation map

• Targets fail after re-run. Open Retrieval Playbook and rebuild with the semantic chunking checklist.
• First call in a fresh deploy crashes. Open Pre-Deploy Collapse.
• Live traffic unstable. Wire probes from Live Monitoring for RAG and follow the Debug Playbook.

---

🔗 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 — Engineers, hackers, and open source builders who supported WFGY from day one.

⭐ WFGY Engine 2.0 is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the Unlock Board.