scriptorium/docs/integrations/openai-compatible-chat.md

OpenAI-Compatible Chat Integration

This is the outbound wire contract for Scriptorium's OpenAI-compatible chat-completions client.

Endpoint And Method

Scriptorium uses the request endpoint override when present; otherwise it uses the configured client base URL. It removes a trailing slash and sends POST /chat/completions.

For example, http://localhost:8000/v1 becomes http://localhost:8000/v1/chat/completions.

Request Payload

The payload always contains model and rendered messages. It additionally contains these fields when applicable:

Field	Inclusion
session_id	Non-empty rendered prompt session ID.
temperature	Non-zero effective value or an explicit zero override.
max_tokens	Non-zero effective value or an explicit zero override.
top_p	Non-zero effective value or an explicit zero override.
service_tier	Any non-empty configured value.
reasoning_effort	Any non-empty configured value.
response_format	Structured output is requested.
provider-specific fields	Flattened from extra_params.

service_tier and reasoning_effort are forwarded without a provider value catalog; the selected backend decides which values it supports.

extra_params are top-level JSON fields, not a nested object. Keys cannot be empty or collide with model, session_id, messages, temperature, max_tokens, top_p, service_tier, reasoning_effort, or response_format. Values must be JSON-serializable.

A rendered session_id is sent as a top-level JSON field, not as a header. Empty values are omitted. The maximum length is 256 Unicode code points.

Messages without cache control use string content. A message with cache control uses one text block:

{
  "role": "system",
  "content": [{
    "type": "text",
    "text": "rendered text",
    "cache_control": {"type": "ephemeral", "ttl": "1h"}
  }]
}

When the prompt omits cache-control ttl, the payload omits ttl. Structured JSON Schema output is sent as:

{
  "response_format": {
    "type": "json_schema",
    "json_schema": {
      "name": "schema name",
      "strict": true,
      "schema": {"type": "object"}
    }
  }
}

Authentication And Timeout

When a direct request API key is present, Scriptorium sends Authorization: Bearer <key> and does not read api_key_env. Otherwise, it resolves the configured non-empty api_key_env at request time and sends the same header. If neither mechanism supplies a key, it sends no Authorization header.

The configured client timeout applies by default. A positive effective timeout_seconds replaces it. An explicit request override of zero disables the HTTP-client timeout; negative values are rejected before a request is sent.

Response Subset And Failures

A successful provider response must supply non-empty choices[0].message.content. Scriptorium reads these optional or required usage fields when present:

• usage.prompt_tokens
• usage.completion_tokens
• usage.total_tokens
• usage.prompt_tokens_details.cached_tokens
• usage.cache_write_tokens

Missing cache usage is reported as zero. Invalid JSON, an empty choices array, or empty first-choice content is a malformed provider response. Network and request-construction failures, non-2xx responses, and malformed responses fail the outbound call. Provider response bodies are not exposed by this client.

The client does not implement built-in retries, tool calls, top-level cache_control, or multi-request payload modes.

Related References

Prompt schema preparation and runner orchestration are described in runner internals. Prompt and profile configuration is defined by the configuration reference.