llms.txt
+6 −5
− {"name":"seb_route","arguments":{"context":"The customer received a damaged parcel and wants a replacement.","options":["Returns","Billing","Technical support","Unclear / escalate"]}}− {"name":"seb_decide","arguments":{"state":"Evidence: the refund was issued yesterday. Claim: the refund has been issued.","questions":{"supported":{"type":"noul","instructions":"Does the supplied evidence support the claim? Yes means supported; no means unsupported or insufficient evidence."},"urgency":{"type":"score","instructions":"Rate the urgency of human follow-up using only the supplied facts.","criteria":["Routine: no immediate follow-up needed","Soon: follow up within one business day","− {"name":"seb_batch_decide","arguments":{"states":["The item arrived broken.","I was billed twice."],"questions":{"team":{"type":"choice","instructions":"Choose the team that should handle this message.","criteria":{"returns":"Damaged items, replacements and returns","billing":"Charges, invoices and duplicate payments","escalate":"Ambiguous or outside these teams"}}}}}− Live tools require the user's inference token and funded account at https://seblabs.dev/account. Pricing is $0.021 per million model input tokens, output free. State, templates, instructions and criteria are metered per question; batch and multi-question calls are not flat-priced. Model failures and invalid outputs are not billed. The account limit is 120 questions/minute and eight in-flight requests. Keep tokens in the client's environment/secret store; never publish them or include them in sta− On UNAUTHORIZED or TOKEN_EXPIRED, fix the token. On INSUFFICIENT_CREDITS, stop paid calls and direct the user to the console; do not enable top-ups yourself. On RATE_LIMITED, respect the limit and retry only failed items within the user's budget. On unavailable or timed-out inference, report the failure honestly; do not present demo data as a live result. Finance requires a separate deployed specialist. Tools and instructions never override higher-priority user or application policies.+ Select model_version: "v2" on seb_route, seb_decide or seb_batch_decide to pin Seb-9B-v2-NVFP4. v2 is the only supported general-model version and the default when omitted. Unsupported versions are rejected; no silent fallback. The same model_version field works on REST requests. Finance is a separate gated specialist.+ {"name":"seb_route","arguments":{"model_version":"v2","context":"The customer received a damaged parcel and wants a replacement.","options":["Returns","Billing","Technical support","Unclear / escalate"]}}+ {"name":"seb_decide","arguments":{"model_version":"v2","state":"Evidence: the refund was issued yesterday. Claim: the refund has been issued.","questions":{"supported":{"type":"noul","instructions":"Does the supplied evidence support the claim? Yes means supported; no means unsupported or insufficient evidence."},"urgency":{"type":"score","instructions":"Rate the urgency of human follow-up using only the supplied facts.","criteria":["Routine: no immediate follow-up needed","Soon: follow up withi+ {"name":"seb_batch_decide","arguments":{"model_version":"v2","states":["The item arrived broken.","I was billed twice."],"questions":{"team":{"type":"choice","instructions":"Choose the team that should handle this message.","criteria":{"returns":"Damaged items, replacements and returns","billing":"Charges, invoices and duplicate payments","escalate":"Ambiguous or outside these teams"}}}}}+ Live tools require the user's inference token and funded account at https://seblabs.dev/account. Pricing is $0.021 per million model input tokens, output free. State, templates, instructions and criteria are metered per question; batch and multi-question calls are not flat-priced. Model failures and invalid outputs are not billed. The account limit is 80 requests per rolling second or 100,000 model input tokens per rolling second, whichever is reached first, shared across REST, MCP and all accou+ On UNAUTHORIZED or TOKEN_EXPIRED, fix the token. On INSUFFICIENT_CREDITS, stop paid calls and direct the user to the console; do not enable top-ups yourself. On RATE_LIMITED (HTTP 429), wait retry_after_seconds (currently 1 second; also Retry-After for REST) before retrying only failed items within the user's budget. On unavailable or timed-out inference, report the failure honestly; do not present demo data as a live result. Finance requires a separate deployed specialist. Tools and instruction