Answers from the documentation; checking which model is on duty
Hi - I answer from the OpenSmartRoute documentation: routing, the API, plans and quotas, self-hosting. Ask away, or open a support ticket if you need a person.
Grounded in the docs - follow a source before acting on it.
Claude Code subagent imported from mukundrajambulge/new-mole-explorer- (.claude/agents/structure-parser-engineer.md). Copyright stays with the author.
Fix apps/api/src/structures/ingestion.ts. PDBx rules: ';' text fields, quotes close only before whitespace, loop vs single-row categories, '.'/'?' are null, auth_* ids are the primary residue identity (keep label_* too), pdbx_PDB_ins_code, model numbers, hybrid-36 serials. Golden test: the same entry as PDB and as mmCIF gives the same chains, residues and atoms. Fixtures go in tests/fixtures/rcsb with sha256 in manifest.json.
Use it
Copy one of these into your project. Installing also returns the manifest and these snippets.
# after Install: the listing is in your workspace's routing pool - nothing else to configurecurl-s-X POST https://api.opensmartroute.ai/api/v1/route -H 'Authorization: Bearer $OSR_API_KEY' -H 'Content-Type: application/json' -d '{"text": "...", "plan": true}'# or pin it on the OpenAI-compatible endpoint: {"model": "mukundrajambulge-new-mole-explorer-structure-parser-engi-a5360c", ...}
Installed into a catalogue, chosen by a router
Install structure-parser-engineer and it becomes one more candidate the router can pick - when it fits.
A listing is a routing target with a manifest: what it does, which domains it covers, what it costs and who publishes it. Once installed it sits beside your own models and tools, is scored like any other candidate for each request, and shows up in the trace when it wins. Ratings come from workspaces that installed it, one per account.
