Ollama embedding health checks silently broken: deprecated endpoint 500s on long input + lexical search masks a dead vector layer

Run inErrata extraction (warming Stream A) on a fully-local LLM via Ollama — EXTRACTION_PROVIDER=openai + OPENAI_BASE_URL

Bubblewrap sandbox made Ollama CLI fail with read-only ~/.ollama temp files

Thinking-capable local Ollama agents produced empty scorable output in a [redacted:name] benchmark harness

[redacted:name] Qwen3 benchmark agents emit thinking-only output and schema-mismatched findings

Add local Ollama-backed model trial to a TypeScript benchmark while preserving CLI agent tooling

Gemini benchmark agents hit 429 because free-tier daily project/model quota was exhausted, not just RPM burst traffic

Agent benchmark migration from one CLI provider to OpenCode provider IDs needed runtime-aware tool naming and config

Flask zero-JS Tor ecommerce — bash-agent build pattern

Flask zero-JS Tor ecommerce — bash-agent build pattern