Agentic AI Atlasby a5c.ai
OverviewWikiGraphFor AgentsEdgesSearchWorkspace
/
GitHubDocsDiscord
iiRecord
Agentic AI Atlas · OpenAI Responses
model-transport:openai-responsesa5c.ai
Search record views/
Record · tabs

Available views

II.Record viewspp. 1 - 1
overviewjsongraph
II.
ModelTransportProtocol overview

model-transport:openai-responses

Reference · live

OpenAI Responses overview

Inspect the raw attributes, linked wiki pages, and inbound or outbound graph edges for model-transport:openai-responses.

ModelTransportProtocolOutgoing · 4Incoming · 30

Attributes

displayName
OpenAI Responses
vendor
OpenAI
specUrl
https://platform.openai.com/docs/api-reference/responses
streamingFraming
sse-or-websocket
toolUseSchema
Tool calls appear as `function_call` items in the response output array with `call_id`, `name`, and `arguments` (JSON string). Tool results are returned as `function_call_output` items referencing the same `call_id`.
thinkingChannel
item
cacheControl
implicit
firstSpecVersion
2025-03-11
currentSpecVersion
2025-03-11
status
standard
requestBodyShape
POST /v1/responses JSON body (top-level fields): - `model` (required, string) - `input` (required, string or array of input items — messages, function_call_output, file/image refs, ...) - `instructions` (optional, string — system-style preamble) - `tools` (optional, array; built-in tools like `web_search`, `file_search`, `code_interpreter`, plus `{type: "function", name, description, parameters}`) - `tool_choice` (optional) - `reasoning` (optional, `{effort: "low"|"medium"|"high", summary?: "auto"|"concise"|"detailed"}`) - `max_output_tokens`, `temperature`, `top_p` (optional) - `stream` (optional, bool) - `previous_response_id` (optional, string — server-side state chaining) - `store` (optional, bool — whether the server should retain this response) - `metadata` (optional, map<string,string>) - `prompt_cache_key` (optional, string — opt-in caching scope key) WebSocket mode uses the same logical body inside a `response.create` event sent to `/v1/responses`; streaming and background fields are transport-owned and should not be forwarded as HTTP-only assumptions.
responseBodyShape
Non-streaming response (HTTP 200 application/json): { "id": "resp_...", "object": "response", "created_at": int, "model": "...", "status": "completed"|"in_progress"|"failed"|"incomplete", "output": [ ], "output_text": string, "usage": { "input_tokens": int, "output_tokens": int, "total_tokens": int, "input_tokens_details": { "cached_tokens": int }, "output_tokens_details": { "reasoning_tokens": int } }, "error": null|{...} }
streamingEventTypes
  • response.created
  • response.in_progress
  • response.output_item.added
  • response.output_item.done
  • response.content_part.added
  • response.content_part.done
  • response.output_text.delta
  • response.output_text.done
  • response.function_call_arguments.delta
  • response.function_call_arguments.done
  • response.reasoning_summary_text.delta
  • response.reasoning_summary_text.done
  • response.completed
  • response.failed
  • response.incomplete
  • error
toolCallWireFormat
A `function_call` item in `response.output[]`: { "type": "function_call", "id": "fc_...", "call_id": "call_...", "name": "<tool_name>", "arguments": "<JSON-encoded string>" }
toolResultWireFormat
A `function_call_output` item provided as input on the next request: { "type": "function_call_output", "call_id": "call_...", "output": "<string>" }
errorEnvelope
Non-2xx response, `application/json`: { "error": { "type": string, "code": string|null, "message": string, "param": string|null } } Common types: `invalid_request_error`, `authentication_error`, `permission_error`, `rate_limit_exceeded`, `server_error`. HTTP status: 400/401/403/404/429/500/503.
cacheControlWireFormat
Implicit automatic prompt caching for prompts >= 1024 tokens; cache state is reported in `usage.input_tokens_details.cached_tokens`. Optional explicit scoping via top-level `prompt_cache_key` (free-form string used by the server to bucket cache entries per project/tenant).
rateLimitSignaling
Response headers on every request: - `x-ratelimit-limit-requests`, `x-ratelimit-remaining-requests`, `x-ratelimit-reset-requests` - `x-ratelimit-limit-tokens`, `x-ratelimit-remaining-tokens`, `x-ratelimit-reset-tokens` On HTTP 429: `retry-after` header (seconds).
reasoningWireFormat
A `reasoning` item in `response.output[]`: { "type": "reasoning", "id": "rs_...", "summary": [ { "type": "summary_text", "text": "..." }, ... ], "encrypted_content"?: "<opaque>", "status": "completed" } Raw chain-of-thought tokens are not exposed; the `summary` items carry user-visible reasoning. `encrypted_content` (when present) is echoed back via `previous_response_id` or input to preserve state.
authHeaderFormat
`Authorization: Bearer <OPENAI_API_KEY>` Optional: `OpenAI-Organization: <org-id>`, `OpenAI-Project: <proj-id>`.
clientRouting
Codex clients should receive proxy endpoints through top-level `openai_base_url` config (preferably `-c openai_base_url=...` for launched sessions). OPENAI_BASE_URL remains a compatibility fallback but is not sufficient for all recent Codex builds and config layers.
versioningHeader
No general API version header; the `/v1/...` path is the surface version. Per-feature betas are opted into with `OpenAI-Beta: <feature>=v<n>` headers (e.g. assistants/threads betas).

Outgoing edges

bridged_by1
  • transport-proxy:adapters-proxy·TransportProxyAgent-Adapter Proxy
realizes1
  • layer:3-transport·LayerTransport
served_by1
  • provider:openai·ModelProviderProductOpenAI
spoken_by1
  • model:gpt-5@current·ModelVersionGPT-5

Incoming edges

bridges1
  • transport-proxy:adapters-proxy·TransportProxyAgent-Adapter Proxy
speaks29
  • agent-core-impl:a5c.core@current·AgentCoreImpla5c Unified Core (current) — unified agent loop
  • agent-core-impl:codex-app-server.core@current·AgentCoreImplCodex App-Server Core (current)
  • agent-core-impl:codex.core@1.x·AgentCoreImplCodex CLI Core (1.x)
  • agent-core-impl:codex-sdk.core@current·AgentCoreImplCodex SDK Core (current)
  • agent-core-impl:codex-websocket.core@current·AgentCoreImplCodex WebSocket Core (current)
  • agent-core-impl:cursor.core@current·AgentCoreImplCursor Core (current)
  • agent-core-impl:hermes.core@current·AgentCoreImplHermes Core (current)
  • agent-core-impl:langgraph.core@current·AgentCoreImplLangGraph Graph Core (current)
  • agent-core-impl:omp.core@current·AgentCoreImplOMP Core (current)
  • agent-core-impl:openai-agents-sdk.core@current·AgentCoreImplOpenAI Agents SDK Core (current)
  • agent-core-impl:openclaw.core@current·AgentCoreImplOpenClaw Core (current)
  • agent-core-impl:opencode.core@1.x·AgentCoreImplOpenCode Core (1.x)
  • agent-core-impl:paperclip.core@current·AgentCoreImplPaperclip Core (current)
  • agent-core-impl:pi.core@current·AgentCoreImplPi Core (current)
  • agent-core-impl:pikiclaw.core@current·AgentCoreImplPikiClaw Core (current)
  • agent-core-impl:symphony.core@current·AgentCoreImplSymphony Core (current)
  • agent-core-impl:vibe-kanban.core@current·AgentCoreImplVibe Kanban Core (current)
  • model:gpt-4o-mini@current·ModelVersionGPT-4o Mini
  • model:gpt-4o@current·ModelVersionGPT-4o
  • model:gpt-5-mini@current·ModelVersionGPT-5 Mini
  • model:gpt-5.3-codex@current·ModelVersionGPT-5.3-Codex
  • model:gpt-5.4-mini@current·ModelVersionGPT-5.4 Mini
  • model:gpt-5.4-nano@current·ModelVersionGPT-5.4 Nano
  • model:gpt-5.4@current·ModelVersionGPT-5.4
  • model:gpt-5.5-pro@current·ModelVersionGPT-5.5 Pro
  • model:gpt-5.5@current·ModelVersionGPT-5.5
  • model:gpt-5@current·ModelVersionGPT-5
  • model:o1@current·ModelVersiono1
  • model:o3@current·ModelVersiono3

Related pages

No related wiki pages for this record.

Shortcuts

Open in graph
Browse node kind