Skip to content

API.md

Latest commit

 

History

History
189 lines (138 loc) · 6.47 KB

API.md

File metadata and controls

189 lines (138 loc) · 6.47 KB

API Reference

This document lists the local HTTP API exposed by ima2 serve.

Base URL:

http://localhost:3333

Provider Policy

Image generation is OAuth-only in the current build.

  • provider: "oauth" is the supported generation path.
  • provider: "api" returns 403 with APIKEY_DISABLED for image generation, edit, and node generation.
  • API keys may still be used by auxiliary developer paths such as billing checks or style-sheet extraction.

Health And Status

Method Path Notes
GET /api/health Server health, version, paths, provider policy
GET /api/providers Provider availability; API-key generation is disabled
GET /api/oauth/status OAuth proxy status and visible models
GET /api/billing Billing/status probe, including API key source when configured

In-Flight Jobs

Method Path Notes
GET /api/inflight Active jobs only by default
GET /api/inflight?includeTerminal=1 Includes recent terminal jobs for debugging
DELETE /api/inflight/:requestId Cancel or forget an active job

In-flight logs and responses use requestId for correlation. Logs should not include raw prompts, reference data URLs, generated base64, tokens, cookies, auth headers, or raw upstream bodies.

Generation

POST /api/generate

Text-to-image and reference-guided root generation.

{
  "prompt": "a shiba in space",
  "quality": "medium",
  "size": "1024x1024",
  "format": "png",
  "moderation": "low",
  "provider": "oauth",
  "model": "gpt-5.4",
  "references": [],
  "requestId": "optional-client-id"
}

Supported quality values: low, medium, high.

Supported moderation values: auto, low.

Recommended model: gpt-5.4. Current app default: gpt-5.4-mini. gpt-5.5 is the strongest quality option when supported, but callers should expect higher quota pressure and possible Codex CLI/backend capability requirements.

POST /api/edit

Image edit / image-to-image generation.

The request includes a prompt and image payload. Like /api/generate, this route rejects provider: "api" unless API-key image generation is intentionally implemented in code.

POST /api/node/generate

Node-mode generation and child edits.

Body fields:

{
  "parentNodeId": "optional-server-node-id",
  "prompt": "continue this image",
  "quality": "medium",
  "size": "1024x1024",
  "format": "png",
  "moderation": "low",
  "model": "gpt-5.4",
  "references": [],
  "externalSrc": "optional-history-url",
  "sessionId": "session-id",
  "clientNodeId": "client-node-id",
  "requestId": "request-id",
  "provider": "oauth"
}

When parentNodeId is present, the server loads the stored parent node image and uses the edit path. Extra node references are currently supported only for root nodes.

The route can stream Server-Sent Events when the client sends Accept: text/event-stream. Possible events include phase, partial, done, and error.

GET /api/node/:nodeId

Fetch stored node metadata and asset URL.

Reference Images

Reference uploads are capped at 5 items. The frontend compresses large JPEG/PNG files before sending them. HEIC/HEIF files are rejected with a user-facing conversion hint.

Server-side validation may return these reference codes:

Code Meaning
REF_NOT_ARRAY references was not an array
REF_TOO_MANY More than the configured reference count
REF_NOT_STRING A reference item was not a string
REF_EMPTY A reference item was empty
REF_TOO_LARGE A reference exceeded the configured base64 size
REF_NOT_BASE64 A reference was not valid base64

History

Method Path Notes
GET /api/history List generated assets
GET /api/history?groupBy=session Group assets by session title
DELETE /api/history/:filename Tombstone a generated asset
POST /api/history/:filename/restore Restore a recently deleted asset

History rows can include node metadata such as sessionId, nodeId, clientNodeId, requestId, and refsCount.

Sessions And Graphs

Method Path Notes
GET /api/sessions List graph sessions
POST /api/sessions Create a session
GET /api/sessions/:id Load a session and graph
PATCH /api/sessions/:id Rename a session
DELETE /api/sessions/:id Delete a session
PUT /api/sessions/:id/graph Save graph snapshot

PUT /api/sessions/:id/graph requires an If-Match header containing the current graph version.

Version mismatch returns GRAPH_VERSION_CONFLICT and the current version. This only means the client saved against a stale graph version; it is not proof that another browser tab changed the graph.

Graph save requests may include observability headers:

X-Ima2-Graph-Save-Id
X-Ima2-Graph-Save-Reason
X-Ima2-Tab-Id

Style Sheets

Method Path Notes
GET /api/sessions/:id/style-sheet Load session style sheet
PUT /api/sessions/:id/style-sheet Save style sheet
PATCH /api/sessions/:id/style-sheet/enabled Toggle style sheet usage
POST /api/sessions/:id/style-sheet/extract Extract style fields from prompt/reference

Style-sheet extraction can require an API key/openai client. This does not reopen API-key image generation.

Common Error Codes

Code Meaning
APIKEY_DISABLED API-key image generation is disabled
INVALID_IMAGE_MODEL Model name is unknown or unsupported
IMAGE_MODEL_UNSUPPORTED Model exists but cannot use image generation
INVALID_MODERATION Moderation value is not auto or low
SAFETY_REFUSAL Upstream safety refusal
MODERATION_REFUSED Content generation refused by moderation
AUTH_CHATGPT_EXPIRED Codex/ChatGPT OAuth session expired
AUTH_API_KEY_INVALID API key is invalid, revoked, out of quota, or wrong org
NETWORK_FAILED Network, proxy, VPN, or firewall failure
OAUTH_UNAVAILABLE Local OAuth proxy is not available
GRAPH_VERSION_REQUIRED Missing graph If-Match header
GRAPH_VERSION_CONFLICT Stale graph version
GRAPH_TOO_LARGE Graph exceeds node/edge limits
NODE_NOT_FOUND Node metadata was not found

CLI Discovery

The server writes an advertisement file at:

~/.ima2/server.json

CLI commands such as ima2 ping, ima2 gen, and ima2 ls use this file unless --server or IMA2_SERVER is provided.