{"id":"transcript-validator","title":"Check tool-call / tool-result pairing and ordering in an LLM transcript (Anthropic, OpenAI Chat, OpenAI Responses)","description":"Validates a message list before it is sent to Anthropic Messages, OpenAI Chat Completions or OpenAI Responses: every tool call paired with its result, results in the right place and role, ids present and unique. Built for an agent that edits, truncates or replays its own history and would otherwise get a 400. Only rules stated in the providers' documentation fail the check; anything else suspicious (for example an unanswered Chat Completions tool call, whose requirement the docs do not state) returns unknown with the reason. Does not validate message content, tool schemas, role alternation or thinking/reasoning blocks, and does not call any provider.","roi":"Finds the orphaned tool_use or dropped function_call_output before the provider rejects the request.","audience":"agent-infra","package":"execution-safety-kit","channels":["x402","mcp"],"endpoint":{"method":"POST","url":"https://agents.writerslogic.com/api/v1/transcript-validator","path":"/api/v1/transcript-validator","contentType":"application/json"},"price":{"amount":"0.005","currency":"USDC","network":"base","perCall":true,"failedCallsCharged":false},"inputSchema":{"type":"object","additionalProperties":false,"required":["provider","messages"],"properties":{"provider":{"type":"string","enum":["anthropic","openai-chat","openai-responses"]},"messages":{"type":"array","minItems":1,"maxItems":500,"items":{"description":"A provider-shaped message (anthropic, openai-chat) or input item (openai-responses)."}},"expectComplete":{"type":"boolean","description":"Default true: a trailing tool call without a result is a defect. Set false when the transcript is mid-loop and results are still pending."}}},"resultSchema":{"type":"object","properties":{"status":{"type":"string","enum":["pass","fail","unknown","unsupported"],"description":"pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass."},"pairs":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"name":{"type":"string"},"callIndex":{"type":"integer"},"resultIndex":{"type":"integer","description":"Absent when unanswered."}}}},"pendingIds":{"type":"array","items":{"type":"string"},"description":"Tool call ids without a result."},"ruleBasis":{"type":"string","description":"Documentation the rules come from."},"witnesses":{"type":"array","items":{"type":"object","properties":{"ruleId":{"type":"string"},"detail":{"type":"string"},"path":{"type":"string","description":"JSON pointer or dotted path into the input."},"offset":{"type":"integer"},"index":{"type":"integer"},"expected":{"description":"What the rule required."},"actual":{"description":"What the input had."}}}},"versions":{"type":"object","description":"Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile)."},"limits":{"type":"array","items":{"type":"string"}},"deterministic":{"type":"boolean","description":"Always true: pure code, no model."}}},"outputSchema":{"type":"object","properties":{"data":{"type":"object","properties":{"status":{"type":"string","enum":["pass","fail","unknown","unsupported"],"description":"pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass."},"pairs":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"name":{"type":"string"},"callIndex":{"type":"integer"},"resultIndex":{"type":"integer","description":"Absent when unanswered."}}}},"pendingIds":{"type":"array","items":{"type":"string"},"description":"Tool call ids without a result."},"ruleBasis":{"type":"string","description":"Documentation the rules come from."},"witnesses":{"type":"array","items":{"type":"object","properties":{"ruleId":{"type":"string"},"detail":{"type":"string"},"path":{"type":"string","description":"JSON pointer or dotted path into the input."},"offset":{"type":"integer"},"index":{"type":"integer"},"expected":{"description":"What the rule required."},"actual":{"description":"What the input had."}}}},"versions":{"type":"object","description":"Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile)."},"limits":{"type":"array","items":{"type":"string"}},"deterministic":{"type":"boolean","description":"Always true: pure code, no model."}}},"_provenance":{"type":"object","description":"C2PA-aligned manifest and W3C VC 2.0 (eddsa-jcs-2022) issued by the hub DID; verify at POST /api/v1/verify-provenance"}},"required":["data","_provenance"]},"example":{"provider":"anthropic","messages":[{"role":"user","content":"Weather in Paris?"},{"role":"assistant","content":[{"type":"tool_use","id":"toolu_1","name":"get_weather","input":{"city":"Paris"}}]},{"role":"user","content":[{"type":"tool_result","tool_use_id":"toolu_1","content":"18C"},{"type":"text","text":"Thanks"}]}]},"openapiOperation":{"operationId":"transcript_validator","summary":"Check tool-call / tool-result pairing and ordering in an LLM transcript (Anthropic, OpenAI Chat, OpenAI Responses)","description":"Validates a message list before it is sent to Anthropic Messages, OpenAI Chat Completions or OpenAI Responses: every tool call paired with its result, results in the right place and role, ids present and unique. Built for an agent that edits, truncates or replays its own history and would otherwise get a 400. Only rules stated in the providers' documentation fail the check; anything else suspicious (for example an unanswered Chat Completions tool call, whose requirement the docs do not state) returns unknown with the reason. Does not validate message content, tool schemas, role alternation or thinking/reasoning blocks, and does not call any provider.\n\nPrice: 0.005 USDC on Base (x402).","x-x402-price-usdc":"0.005","x-x402-amount":"5000","x-payment-info":{"protocols":["x402"],"price":{"mode":"fixed","currency":"USD","amount":"0.005"}},"x-audience":"agent-infra","x-sample-url":"https://agents.writerslogic.com/api/v1/samples/transcript-validator","security":[{"x402":[]},{"apiKey":[]}],"requestBody":{"required":true,"content":{"application/json":{"schema":{"type":"object","additionalProperties":false,"required":["provider","messages"],"properties":{"provider":{"type":"string","enum":["anthropic","openai-chat","openai-responses"]},"messages":{"type":"array","minItems":1,"maxItems":500,"items":{"description":"A provider-shaped message (anthropic, openai-chat) or input item (openai-responses)."}},"expectComplete":{"type":"boolean","description":"Default true: a trailing tool call without a result is a defect. Set false when the transcript is mid-loop and results are still pending."}}},"example":{"provider":"anthropic","messages":[{"role":"user","content":"Weather in Paris?"},{"role":"assistant","content":[{"type":"tool_use","id":"toolu_1","name":"get_weather","input":{"city":"Paris"}}]},{"role":"user","content":[{"type":"tool_result","tool_use_id":"toolu_1","content":"18C"},{"type":"text","text":"Thanks"}]}]}}}},"responses":{"200":{"description":"Paid result with provenance","content":{"application/json":{"schema":{"type":"object","properties":{"data":{"type":"object","properties":{"status":{"type":"string","enum":["pass","fail","unknown","unsupported"],"description":"pass: every rule held. fail: a rule was violated (see witnesses). unknown: the input lacks the evidence to decide. unsupported: outside what this engine covers. Missing evidence is never a pass."},"pairs":{"type":"array","items":{"type":"object","properties":{"id":{"type":"string"},"name":{"type":"string"},"callIndex":{"type":"integer"},"resultIndex":{"type":"integer","description":"Absent when unanswered."}}}},"pendingIds":{"type":"array","items":{"type":"string"},"description":"Tool call ids without a result."},"ruleBasis":{"type":"string","description":"Documentation the rules come from."},"witnesses":{"type":"array","items":{"type":"object","properties":{"ruleId":{"type":"string"},"detail":{"type":"string"},"path":{"type":"string","description":"JSON pointer or dotted path into the input."},"offset":{"type":"integer"},"index":{"type":"integer"},"expected":{"description":"What the rule required."},"actual":{"description":"What the input had."}}}},"versions":{"type":"object","description":"Every semantic dependency of this answer (engine, tables and their as-of dates, tokenizer, calendar, rounding profile)."},"limits":{"type":"array","items":{"type":"string"}},"deterministic":{"type":"boolean","description":"Always true: pure code, no model."}}},"_provenance":{"type":"object","description":"C2PA-aligned manifest and W3C VC 2.0 (eddsa-jcs-2022) issued by the hub DID; verify at POST /api/v1/verify-provenance"}},"required":["data","_provenance"]}}}},"400":{"description":"Invalid request (no payment consumed)","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"string"},"code":{"type":"string"}}}}}},"401":{"description":"Invalid X-API-KEY","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"string"},"code":{"type":"string"}}}}}},"402":{"description":"Payment required or invalid","content":{"application/json":{"schema":{"type":"object","description":"x402 v2 PaymentRequired (also base64 in the PAYMENT-REQUIRED header)","properties":{"x402Version":{"type":"integer"},"error":{"type":"string"},"code":{"type":"string"},"resource":{"type":"object"},"accepts":{"type":"array","items":{"type":"object"}},"extensions":{"type":"object"}}}}}},"502":{"description":"Upstream failure; the payment is released or not settled","content":{"application/json":{"schema":{"type":"object","properties":{"error":{"type":"string"},"code":{"type":"string"}}}}}}}},"links":{"docs":"https://agents.writerslogic.com/docs/transcript-validator/","docsJson":"https://agents.writerslogic.com/docs/transcript-validator.json","sample":"https://agents.writerslogic.com/api/v1/samples/transcript-validator","openapi":"https://agents.writerslogic.com/openapi.json","catalog":"https://agents.writerslogic.com/api/v1/catalog","verifyProvenance":"https://agents.writerslogic.com/api/v1/verify-provenance","index":"https://agents.writerslogic.com/docs/index.json"}}