Create rollout_readiness_gate.md

This commit is contained in:
PSBigBig 2025-08-31 17:59:15 +08:00 committed by GitHub
parent 1e438a71dd
commit a98161e6f6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -0,0 +1,153 @@
# 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](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md)
- Retrieval knobs: [Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
- Traceability schema: [Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md)
- Snippet and citation contract: [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
- Embedding vs meaning: [Embedding ≠ Semantic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
- Hallucination and chunk boundaries: [Hallucination](https://github.com/onestardao/WFGY/blob/main/ProblemMap/hallucination.md)
- Long chains and entropy: [Context Drift](https://github.com/onestardao/WFGY/blob/main/ProblemMap/context-drift.md), [Entropy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/entropy-collapse.md)
- Logic collapse and recovery: [Logic Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md)
- Prompt injection fences: [Prompt Injection](https://github.com/onestardao/WFGY/blob/main/ProblemMap/prompt-injection.md)
- Boot order and deploy traps: [Bootstrap Ordering](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md), [Deployment Deadlock](https://github.com/onestardao/WFGY/blob/main/ProblemMap/deployment-deadlock.md), [Pre-Deploy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md)
- Live ops after ship: [Live Monitoring for RAG](https://github.com/onestardao/WFGY/blob/main/ProblemMap/ops/live_monitoring_rag.md), [Debug Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/ops/debug_playbook.md)
## 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](https://github.com/onestardao/WFGY/blob/main/ProblemMap/bootstrap-ordering.md).
2) **RAG quality probe**
- Run a 2040 item gold set.
- Score with: [RAG Precision/Recall Eval](https://github.com/onestardao/WFGY/blob/main/ProblemMap/eval/eval_rag_precision_recall.md) and [Semantic Stability Eval](https://github.com/onestardao/WFGY/blob/main/ProblemMap/eval/eval_semantic_stability.md).
- Fail if any target above is missed.
3) **Hallucination fence**
- Enforce cite-then-explain. Verify with [Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md) and [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md).
- 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](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md).
- If recall varies with HyDE or BM25, lock the two-stage query and rerank. See [Query Parsing Split](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_query_parsing_split.md).
- Fragmented stores: see [Vectorstore Fragmentation](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_vectorstore_fragmentation.md).
5) **Chain stability**
- If chains exceed safe length and entropy rises, split and bridge. See [Context Drift](https://github.com/onestardao/WFGY/blob/main/ProblemMap/context-drift.md) and [Entropy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/entropy-collapse.md).
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
```yaml
# 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](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md) and rebuild with the semantic chunking checklist.
* First call in a fresh deploy crashes. Open [Pre-Deploy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.md).
* Live traffic unstable. Wire probes from [Live Monitoring for RAG](https://github.com/onestardao/WFGY/blob/main/ProblemMap/ops/live_monitoring_rag.md) and follow the [Debug Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/ops/debug_playbook.md).
---
### 🔗 Quick-Start Downloads (60 sec)
| Tool | Link | 3-Step Setup |
| -------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ | ---------------------------------------------------------------------------------------- |
| **WFGY 1.0 PDF** | [Engine Paper](https://github.com/onestardao/WFGY/blob/main/I_am_not_lizardman/WFGY_All_Principles_Return_to_One_v1.0_PSBigBig_Public.pdf) | 1⃣ Download · 2⃣ Upload to your LLM · 3⃣ Ask “Answer using WFGY + \<your question>” |
| **TXT OS (plain-text OS)** | [TXTOS.txt](https://github.com/onestardao/WFGY/blob/main/OS/TXTOS.txt) | 1⃣ Download · 2⃣ Paste into any LLM chat · 3⃣ 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 →](https://github.com/onestardao/WFGY/tree/main/core/README.md) |
| Problem Map 1.0 | Initial 16-mode diagnostic and symbolic fix framework | [View →](https://github.com/onestardao/WFGY/tree/main/ProblemMap/README.md) |
| Problem Map 2.0 | RAG-focused failure tree, modular fixes, and pipelines | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) |
| Semantic Clinic Index | Expanded failure catalog: prompt injection, memory bugs, logic drift | [View →](https://github.com/onestardao/WFGY/blob/main/ProblemMap/SemanticClinicIndex.md) |
| Semantic Blueprint | Layer-based symbolic reasoning & semantic modulations | [View →](https://github.com/onestardao/WFGY/tree/main/SemanticBlueprint/README.md) |
| Benchmark vs GPT-5 | Stress test GPT-5 with full WFGY reasoning suite | [View →](https://github.com/onestardao/WFGY/tree/main/benchmarks/benchmark-vs-gpt5/README.md) |
| 🧙‍♂️ Starter Village 🏡 | New here? Lost in symbols? Click here and let the wizard guide you through | [Start →](https://github.com/onestardao/WFGY/blob/main/StarterVillage/README.md) |
---
> 👑 **Early Stargazers: [See the Hall of Fame](https://github.com/onestardao/WFGY/tree/main/stargazers)**
> Engineers, hackers, and open source builders who supported WFGY from day one.
> <img src="https://img.shields.io/github/stars/onestardao/WFGY?style=social" alt="GitHub stars"> ⭐ [WFGY Engine 2.0](https://github.com/onestardao/WFGY/blob/main/core/README.md) is already unlocked. ⭐ Star the repo to help others discover it and unlock more on the [Unlock Board](https://github.com/onestardao/WFGY/blob/main/STAR_UNLOCKS.md).
<div align="center">
[![WFGY Main](https://img.shields.io/badge/WFGY-Main-red?style=flat-square)](https://github.com/onestardao/WFGY)
 
[![TXT OS](https://img.shields.io/badge/TXT%20OS-Reasoning%20OS-orange?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS)
 
[![Blah](https://img.shields.io/badge/Blah-Semantic%20Embed-yellow?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlahBlahBlah)
 
[![Blot](https://img.shields.io/badge/Blot-Persona%20Core-green?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlotBlotBlot)
 
[![Bloc](https://img.shields.io/badge/Bloc-Reasoning%20Compiler-blue?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlocBlocBloc)
 
[![Blur](https://img.shields.io/badge/Blur-Text2Image%20Engine-navy?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlurBlurBlur)
 
[![Blow](https://img.shields.io/badge/Blow-Game%20Logic-purple?style=flat-square)](https://github.com/onestardao/WFGY/tree/main/OS/BlowBlowBlow)
 
</div>