jbeasley/openclaw-workspace-2026

Files

T

JC Beasley 0bd719ab91 Add cross-project pattern registry for retrieval-augmented generalization

- Create patterns/ directory with README, manifest, and 10 initial patterns
  covering Ollama JSON fallback, API escaping, deprecation, PTY auth,
  queue-poll, LLM-as-parser, credential rotation, reverse proxy binding,
  human approval gates, and transient retry.
- Wire pattern loading into architecture/pipeline.js based on task tags.
- Update architecture/orchestrator.js to load patterns and surface them in
  the system prompt.
- Update MEMORY.md, ARCHITECTURE.md, and CONTEXT.md to document the registry
  and record the decision.

2026-08-06 12:46:09 -07:00

1.8 KiB

Raw Blame History

Pattern: Ollama Structured Output Fallback

Symptom

A workflow calls a local Ollama model (e.g., gemma3:4b, small quantized models) with a structured-output or JSON schema request, but the returned text is not valid JSON, misses required fields, wraps the JSON in prose, or otherwise fails schema validation.

Affected Projects

Cyber Tips Newsletter pipeline
Proxmox VE snapshot summarizer
AI video generation pipeline (ComfyUI + WAN 2.1 payloads)
Forex trading analysis workflow

Root Cause

Small local instruction-tuned models have weaker schema adherence than frontier APIs. They may produce JSON-like text that does not strictly conform to the requested schema, especially under complex prompts or when asked to combine generation with strict formatting.

Standard Fix

Add a downstream JavaScript Code node (or equivalent parser) in n8n that:

Attempts a strict JSON.parse() first.
On failure, applies regex-based JSON extraction to pull the first {...} or [...] block from the text.
Optionally sanitizes common issues (trailing commas, unescaped newlines, code fences).
Falls back to a safe default or error flag if extraction still fails.

This is a deliberate workaround, not a substitute for fixing the model. Document it as such wherever applied.

When to Apply

Any new n8n workflow that uses a local Ollama model for structured extraction, classification, or JSON generation.
Any integration where the downstream node requires strict JSON and the LLM is under ~8B parameters or known to drift.

Verification

Test the fallback with intentionally malformed LLM output.
Confirm downstream nodes receive valid parsed JSON.
Log fallback events so model quality can be monitored separately.

json-escaping-downstream-api
llm-as-parser-fallback

1.8 KiB Raw Blame History