feat: LLM-native structured output via JSON schema enforcement#1037
Merged
Conversation
Thread existing JSON schemas from prompt definitions through the text-completion service to LLM backends' native structured output APIs. When a prompt has response-type "json" and a strict-mode compatible schema, the LLM constrains token selection at the logit level to guarantee schema-valid output. Wire-level changes: - Add response_format and schema fields to TextCompletionRequest - Update translator to encode/decode new fields - Pass new fields through LlmService, TextCompletionClient, and PromptManager Runtime schema compatibility checker: - New is_strict_mode_compatible() utility validates schemas against LLM provider constraints (additionalProperties, required fields, no unsupported constraints, no open-ended objects) - Per-prompt eligibility decision: compliant schemas use structured output, non-compliant schemas fall back to free-text + post-hoc validation LLM backend implementations: - OpenAI: response_format with json_schema, variant-aware top-level array rejection (openai variant blocks, llama/vllm variants allow) - New vllm variant for the OpenAI backend - vLLM (dedicated): response_format in raw HTTP body - Ollama: format=<schema> parameter - Claude: tool-use trick (forced tool call with schema as input_schema) - Mistral: native json_schema response_format - Llamafile, LM Studio: OpenAI SDK response_format - Azure OpenAI: AzureOpenAI SDK response_format - Azure serverless: response_format in raw HTTP body - TGI: response_format in raw HTTP body - VertexAI Gemini: response_mime_type + response_schema - VertexAI Claude: tool-use trick - Google AI Studio: response_mime_type + response_schema - Bedrock, Cohere: signature-only (no structured output yet) Post-hoc jsonschema.validate() retained as defence-in-depth. Tech spec added: docs/tech-specs/structured-output.md Update tests
Contributor License Agreement ✅All contributors have signed the CLA. Thank you! |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
is_strict_mode_compatible) that performs per-prompt eligibility decisions — compliant schemas use structured output, non-compliant schemas fall back to free-text + post-hoc validationChanges
response_formatandschemafields added toTextCompletionRequest, translator, client, and service layersschema_compatibility.pyvalidates strict-mode constraints (additionalProperties, required, no unsupported keywords)docs/tech-specs/structured-output.mdwith phased rollout planjsonschema.validate()retained as defence-in-depthTest plan
is_strict_mode_compatible(30 cases covering all paths)