dev-5090 uncensored inference

Fix broken JSON (trailing commas, single quotes, unquoted keys). Returns only valid JSON.

Convert a curl command to Python/JS/Go. Specify target language in the message.

Uncensored general chat (Qwen3.8-27B Heretic).

Generate tests for a code snippet (matches file's existing test framework).

Explain a regex in plain English. Paste the regex in message content.

Explain a SQL query in plain English. Paste query in message.

Pay-to-compose orchestrator: pulls live data (weather), routes it through two local-model stages, then an independent judge verifies the result against the source data before it ships (one bounded self-correction on rejection). Returns the composed answer, the judge's verdict, and a per-step cost ledger.

Proof-of-Model: detect silent model substitution at any OpenAI-compatible inference endpoint. mode=fingerprint records what a seller serves today; mode=verify re-probes later and proves whether the weights changed. Deterministic, evidence included, no model used to judge.

Agent-readiness audit of any public URL: score /100 with per-check raw evidence, published weights, and a recompute recipe. Deterministic — no model, same input gives the same score.

Uncensored coder completions, served by Qwen3.8-27B abliterated (Heretic) on a local RTX 5090 via vLLM.

Refactor code while preserving behavior. Returns diff + rationale.

Structured code review: correctness, security, edge cases, reuse. Returns numbered findings.

Security audit of code snippet (SQLi, XSS, auth bypass, secret leaks, unsafe deserialization).

Text embeddings (768-dim). Send {"input": "text"} or {"input": ["a","b"]}.

Multi-step reasoning and planning, served by Qwen3.8-27B abliterated (Heretic) on a local RTX 5090 via vLLM.

Build a regex from a natural-language description. Returns just the regex + one test string.

Complete a full agentic task (plan → generate → verify). Longer running.

Explain code snippet in plain English (paste code in message).

Embed and index documents into a private vector collection (768-dim, cosine). documents=[{id,text,metadata}], namespace picks the collection. Returns documents, chunks, tokens and latency.

Search a namespace you indexed: the query is embedded on the same model and matched against your collection. Returns hits with score, text and metadata, plus latency.

Summarize a document without it leaving this machine. mode=bullets|paragraph|key-points, max_words caps the length. Returns the summary, the model that wrote it, token usage and latency.

Translate text into a target language (ISO code: es, de, fr, ja, pt, pl...). Optional domain and tone hints. Returns the translation, the model, usage and latency.

[preview] Image understanding. Currently TEXT-FALLBACK ONLY — no vision model is loaded. Priced accordingly.