MelisAIEngineGemini

Google Gemini provider for the Melis AI engine — package melisplatform/melis-ai-engine-gemini.

Purpose

MelisAIEngineGemini is the concrete Google Gemini implementation of MelisAIEngine's MelisAIEngineModelService contract. It supplies Gemini-specific HTTP client setup, the generateContent payload shape (the contents / parts schema), tool/function-call mapping, file handling via the File API or inline embed, and token-usage parsing. The module is stateless (no tables of its own) and ships no UI — all AI screens are provided by melis-ai / melis-ai-engine.

Enable it

Add to config/melis.module.load.php:

php

return [
    'MelisAIEngineGemini',
];

Requires melisplatform/melis-ai-engine ^5.3. The engine selects this provider automatically at runtime when the active model's company name contains Google and this module is installed; it builds MelisAIEngineModelGeminiService via $serviceManager->build(MelisAIEngineModelGeminiService::class, ['modelId' => …, 'agentId' => …]).

Key services

Service alias	Role
`MelisAIEngineModelGeminiService`	The Gemini provider — subclass of `MelisAIEngineModelService`, built per request with `modelId` + `agentId`.

Notable methods of MelisAIEngineModelGeminiService:

Method	Gemini implementation
`setClient()`	Builds a `Laminas\Http\Client` POSTing to `{api_url}/models/{mam_generative_model}:generateContent?key={apiKey}`. The API key is a URL query parameter (not a header). Long timeout.
`getMessageKey()`	Returns `'contents'`.
`addToolsToPayload()`	Fetches tools via `getAgentFunctions()`, sanitises each, renames `input_schema` → `parameters`, and wraps as `tools:[{functionDeclarations:[…]}]` with `toolConfig.functionCallingConfig.mode='AUTO'`. Falls back to a `url_context` tool when no functions are present.
`constructContent()` / `addContentToPayload()`	Maps role `assistant` → `model`; builds `parts` arrays containing `{text}`, `{fileData:{fileUri,mimeType}}` (File API), or `{inlineData:{mimeType,data}}` (base64).
`sendCustomAI()`	POSTs JSON payload (retries on 5xx / 429); parses `candidates[].content.parts[]` for text and `functionCall` entries; dispatches each tool call (MCP or built-in); appends results as `{functionResponse:{name,response:{result}}}` and loops until no more tool calls, a `finishReason`, or a safety cap.
`processFiles()` / `processContextFiles()`	Handles file uploads per `mam_file_upload_mode` (see File upload modes); also stores a copy via `uploadDocument()` for session display.
`setPromptTokenCount()` / `setResponseTokenCount()` / `setTotalTokenCount()`	Read `usageMetadata.promptTokenCount`, `candidatesTokenCount`, `totalTokenCount`.
`getAllowedMimetypes()`	Returns the allowed MIME types from the Gemini config block.

File upload modes

The model's mam_file_upload_mode controls how files reach Gemini:

fileapi (default) — uploads to the Gemini File API via a multipart POST, then polls until the file state is ACTIVE, and references the returned fileApiUri.
embed — sends file bytes inline as base64 (inlineData), with text extraction for supported formats.

Configuration

Config lives under config['plugins']['melisaiengine']['datas']['AI']['Gemini']:

Key	Purpose
`api_url`	Base URL for `generateContent` requests.
`upload_url`	Gemini File API upload endpoint.
`allowed_mimetypes`	Accepted MIME types (returned by `getAllowedMimetypes()`).

The API key comes from the model's platform key record (mapk_*), managed in the AI backoffice. It is not stored in config files and has no environment-variable fallback.

API key in URL

The Google API key is appended as a query parameter (?key=…). Request logs and HTTP proxies may capture it — ensure your infrastructure limits log retention accordingly.

Tool / function-call mapping

Gemini uses parameters where the engine contract uses input_schema; addToolsToPayload() performs this rename before sending. Tool calls arrive as {functionCall:{name,args}} with no id (positional, unlike Claude's tool_use_id). The service routes by name via MelisAIEngineMcpService::isMcpTool() and returns {functionResponse:{name,response:{result:…}}}.

Differences vs Claude provider

Aspect	Gemini	Claude
Message key	`contents`	`messages`
Assistant role label	`model`	`assistant`
Tool schema key	`parameters`	`input_schema`
Tool-call id	none (positional)	`tool_use_id`
Auth method	URL query param `?key=`	`x-api-key` header
Default file mode	`fileapi`	`embed`

Key files

Concern	Path
Provider service	`vendor/melisplatform/melis-ai-engine-gemini/src/Service/MelisAIEngineModelGeminiService.php`

MelisAIEngineGemini ​

Purpose ​

Enable it ​

Key services ​

File upload modes ​

Configuration ​

Tool / function-call mapping ​

Differences vs Claude provider ​

Key files ​

See also ​