Create smolagents.md

This commit is contained in:
PSBigBig 2025-08-27 14:19:15 +08:00 committed by GitHub
parent afb8a0c7bf
commit c8d5087cfb
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -0,0 +1,237 @@
# Smolagents: Guardrails and Fix Patterns
Use this page when your orchestration uses **smolagents** (ToolCallingAgent, CodeAgent, multi agent flows) and you see tool loops, wrong snippets, role mixing, or answers that flip between runs. The table maps symptoms to exact WFGY fix pages and gives a minimal recipe you can paste.
**Acceptance targets**
- ΔS(question, retrieved) ≤ 0.45
- Coverage ≥ 0.70 to the intended section or record
- λ stays convergent across 3 paraphrases and 2 seeds
- E_resonance stays flat on long windows
---
## Open these first
- Visual map and recovery
[RAG Architecture & Recovery](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md)
- End to end retrieval knobs
[Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
- Why this snippet
[Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md)
- Ordering control
[Rerankers](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md)
- Embedding vs meaning
[Embedding ≠ Semantic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md)
- Hallucination and chunk edges
[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)
- Structural collapse and recovery
[Logic Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md)
- Prompt injection and schema locks
[Prompt Injection](https://github.com/onestardao/WFGY/blob/main/ProblemMap/prompt-injection.md)
- Multi agent conflicts
[Multi-Agent Problems](https://github.com/onestardao/WFGY/blob/main/ProblemMap/Multi-Agent_Problems.md)
- Bootstrap and deployment ordering
[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)
- Snippet and citation schema
[Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
---
## Typical smolagents breakpoints and the right fix
- **ToolCallingAgent returns free text instead of strict JSON**
Enforce schema via a contract gate and echo the schema each step.
Open: [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md) · [Prompt Injection](https://github.com/onestardao/WFGY/blob/main/ProblemMap/prompt-injection.md)
- **CodeAgent executes but results drift or timeout cascades**
Add BBCR bridge steps, strict timeouts, and idempotency before side effects.
Open: [Logic Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md)
- **High similarity yet wrong meaning**
Mixed write and read embeddings, metric mismatch, or fragmented stores.
Open: [Embedding ≠ Semantic](https://github.com/onestardao/WFGY/blob/main/ProblemMap/embedding-vs-semantic.md) · [Vectorstore Fragmentation](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_vectorstore_fragmentation.md)
- **Hybrid retrieval worse than single retriever**
Two stage query drift or mis weighted rerank.
Open: [Query Parsing Split](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_query_parsing_split.md) · [Rerankers](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md)
- **Citations missing or inconsistent across tools**
Require cite then explain and lock snippet fields at the agent boundary.
Open: [Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md) · [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
- **Agent handoff loops or shared memory overwrites**
Split memory namespaces and stamp `mem_rev` and `mem_hash`.
Open: [Multi-Agent Problems](https://github.com/onestardao/WFGY/blob/main/ProblemMap/Multi-Agent_Problems.md) · [role drift](https://github.com/onestardao/WFGY/blob/main/ProblemMap/multi-agent-chaos/role-drift.md) · [memory desync](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_memory_desync.md)
---
## Fix in 60 seconds
1) **Measure ΔS**
Compute ΔS(question, retrieved) and ΔS(retrieved, expected anchor).
Stable < 0.40, transitional 0.40 to 0.60, risk 0.60.
2) **Probe λ_observe**
Do a k sweep in retrieval and reorder prompt headers. If λ flips, lock the schema and clamp with BBAM.
3) **Apply the module**
- Retrieval drift → BBMC plus [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
- Reasoning collapse → BBCR bridge plus BBAM, verify with [Logic Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md)
- Hallucination re entry after correction → [Pattern: Hallucination Re-entry](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_hallucination_reentry.md)
4) **Verify**
Coverage ≥ 0.70. ΔS ≤ 0.45. Three paraphrases and two seeds with λ convergent.
---
## Minimal smolagents pattern with WFGY checks
```python
# Pseudocode: show only the control points that matter.
from smolagents import Tool, ToolCallingAgent # placeholder imports for illustration
# Contracted snippet schema
SNIPPET_FIELDS = ["snippet_id", "section_id", "source_url", "offsets", "tokens"]
def retriever_search(q, k=10):
# unified analyzer and metric across dense and sparse
# return a list[dict] of snippets with SNIPPET_FIELDS populated
return retriever.search(q, k=k)
@Tool
def retrieve(q: str) -> list:
"Return auditable snippets with the locked schema."
return retriever_search(q, k=10)
def assemble_prompt(context, q):
# schema-locked prompt, cite first, then answer
return prompt.format(context=context, question=q)
def wfgy_gate(q, context, answer):
# compute ΔS(question, context) and log λ, enforce thresholds
metrics = metrics_and_trace(q, context, answer)
if metrics["risk"]:
raise RuntimeError("WFGY gate: high ΔS or divergent λ")
return metrics
agent = ToolCallingAgent(
tools=[retrieve],
# keep tool arguments strict and echo the schema on each tool call
)
def run(question: str):
context = retrieve(question)
msg = assemble_prompt(context, question)
# the agent should obey cite-then-explain and strict JSON where required
result = agent.run(msg)
metrics = wfgy_gate(question, context, result)
return {"answer": result, "metrics": metrics}
````
**What this enforces**
* Retrieval is observable and parameterized. Analyzer and metric stay unified.
* Prompt is schema locked with cite first and strict JSON for tool outputs.
* A post generation WFGY gate can halt the run when ΔS is high or λ flips.
* Traces record snippet to citation mapping for audits.
Specs and recipes
[RAG Architecture & Recovery](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rag-architecture-and-recovery.md) ·
[Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md) ·
[Retrieval Traceability](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-traceability.md) ·
[Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
---
## Smolagents-specific gotchas
* `@Tool` signatures inferred too loosely and allow free form text. Tighten types and validate arguments before execution.
See [Data Contracts](https://github.com/onestardao/WFGY/blob/main/ProblemMap/data-contracts.md)
* CodeAgent side effects outside the intended sandbox. Make the steps idempotent and restrict file system or network access.
See [Logic Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/logic-collapse.md)
* Hybrid retrievers degrade compared to single retriever. Unify analyzer and metric, then add deterministic reranking.
See [Query Parsing Split](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_query_parsing_split.md) · [Rerankers](https://github.com/onestardao/WFGY/blob/main/ProblemMap/rerankers.md)
* Memory overwrite or hidden role drift in multi agent flows. Split namespaces and stamp `mem_rev` and `mem_hash`.
See [Multi-Agent Problems](https://github.com/onestardao/WFGY/blob/main/ProblemMap/Multi-Agent_Problems.md) · [role drift](https://github.com/onestardao/WFGY/blob/main/ProblemMap/multi-agent-chaos/role-drift.md) · [memory desync](https://github.com/onestardao/WFGY/blob/main/ProblemMap/patterns/pattern_memory_desync.md)
* Long chains flatten style and drift logically. Split the plan, then re join with a BBCR bridge and clamp with BBAM.
See [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)
---
## When to escalate
* ΔS remains ≥ 0.60
Rebuild the index using the checklists and verify with a small gold set.
[Retrieval Playbook](https://github.com/onestardao/WFGY/blob/main/ProblemMap/retrieval-playbook.md)
* Identical input yields different answers across runs
Check version skew and session state.
[Pre-Deploy Collapse](https://github.com/onestardao/WFGY/blob/main/ProblemMap/predeploy-collapse.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>
要我直接做第三頁 **rewind\_agents.md** 嗎?