MelisAIEngineClaude

Anthropic Claude provider for the Melis AI engine — a backend engine with no React UI of its own. Package melisplatform/melis-ai-engine-claude.

Purpose

MelisAIEngineClaude is the concrete Anthropic Claude provider for the MelisAI suite. It extends the engine's MelisAIEngineModelService contract and supplies Claude-specific HTTP client setup, the Anthropic Messages API payload shape, file handling, tool/function mapping and response parsing. The module is stateless — it owns no database tables; all runtime state lives in the engine's own tables.

The engine selects this provider automatically at runtime when the active model's company contains Anthropic (and this module is installed).

Role in the React back-office

This module has no React back-office tool and no UI of its own: no ui-react/ brick, no config/react-api.php, no capabilities and no controller. It never appears as a tool, menu node or sidebar entry in /melis-react. It is pure plumbing — the code path that lets Melis talk to Claude.

Its only visible effect in the React back-office is transitive, through MelisAI:

Its install/dbdeploy/*.sql scripts seed the company Anthropic and several Claude models into the engine's model catalog.
Those models then appear as choices in the MelisAI admin (Platform AI / model settings), under the Anthropic company.
To use one you store your Anthropic API key on that model row (mapk_*), then point an instance / agent at the Claude model.
From then on every chat on that agent — including the React AI Assistant — routes through this provider.

You never open this module. In /melis-react it is only ever a line in a model dropdown surfaced by MelisAI, plus the engine behind AI chats that use it. If Claude chats fail, the cause is usually a missing API key on the model row or an inactive model — both configured in MelisAI, not here.

Enable it

Add to config/melis.module.load.php after the AI engine:

php

return [
    'MelisAIEngine',
    'MelisAIEngineClaude',
];

Dependency: melisplatform/melis-ai-engine ^6.0. The Anthropic API key is stored per model in the Melis AI back-office (the model's mapk_* key row) — not in a config file or environment variable.

Key services

Service alias	Role
`MelisAIEngineModelClaudeService`	The Claude provider. Extends `MelisAIEngineModelService` and implements the Anthropic Messages API contract. Built by the service manager with `['modelId' => …, 'agentId' => …]` factory options.

Notable methods on MelisAIEngineModelClaudeService:

Method	Role
`setClient()`	Builds a `Laminas\Http\Client` POSTing to the configured Claude Messages URL. Sets headers `Content-Type/Accept: application/json`, `x-api-key` (from the model's API key), `anthropic-version: 2023-06-01`, and an `anthropic-beta` header enabling prompt-caching and web-fetch betas. Uses a long timeout to accommodate tool-use loops.
`getMessageKey()`	Returns `'messages'`.
`addToolsToPayload()`	Reads agent functions via `getAgentFunctions()`, strips internal engine keys (`mcp`, `type`, `server`, `module`, `max_silence`, `operation_timeout`) via `sanitizeToolForClaudeAPI()`, appends tools in Anthropic shape (`name`, `description`, `input_schema`), appends the built-in `web_fetch` tool, and deduplicates by name.
`constructContent()` / `addContentToPayload()`	Maps role `model` to `assistant`; builds Anthropic content blocks (`{type:text}`, `{type:image, source:{url\|base64,…}}`, `{type:document, source:{…, media_type:application/pdf}}`); appends to `payload['messages']`.
`sendCustomAI()`	Injects `model` (`mam_generative_model`) and `max_tokens`; POSTs JSON with retries on 5xx; parses `content[]` into text and `tool_use` blocks; dispatches each tool (MCP via `MelisAIEngineMcpService::invokeTool`, otherwise built-in); appends results as `{type:tool_result, tool_use_id, content}` in a `user` message; loops until `stop_reason === 'end_turn'` or a safety hop-cap is reached. Enables prompt caching.
`processFiles()` / `processContextFiles()`	Converts uploads per the model's `mam_file_upload_mode` (default: `embed`): DOCX/XLSX → extracted text, images/PDF → base64, or via `uploadDocument()` when internal upload is enabled.
`setPromptTokenCount()` / `setResponseTokenCount()` / `setTotalTokenCount()`	Read `responseData['usage']` fields (`input_tokens`, `output_tokens`, plus cache-read/creation counters); total = input + output.
`getAllowedMimetypes()`	Returns allowed upload MIME types from the Claude config block.
`continueConversation()`	Rehydrates message history from saved state and calls `sendCustomAI()` again for multi-hop tool-use continuation.

Tool / function-calling

Engine tools already use Anthropic's input_schema shape, so addToolsToPayload() primarily sanitises and forwards them. A model tool call arrives as {type:'tool_use', name, id, input}; the service extracts name / input / id, routes via MelisAIEngineMcpService::isMcpTool() (MCP invokeTool vs. built-in function), and returns the result as {type:'tool_result', tool_use_id:<id>, content:<json>} inside a user message, then continues the loop. The id field correlates call↔result as required by the Anthropic API.

Configuration

Provider settings live under:

config['plugins']['melisaiengine']['datas']['AI']['Claude']

Key	Purpose
`api_url`	The Anthropic Messages API endpoint URL (`https://api.anthropic.com/v1/messages`).
`allowed_mimetypes`	MIME types accepted for file uploads.

A sibling ['AI']['Anthropic'] block declares the file-upload modes (embed) and internal-upload support. The API key is not read from config or environment — it comes exclusively from the model's DB key row (mapk_*), entered by an admin in the MelisAI admin.

Seeded models

Installed via install/dbdeploy/*.sql under the company Anthropic; the mam_status flag decides which are offered:

`mam_generative_model`	Model
`claude-opus-4-8`	Claude Opus 4.8
`claude-sonnet-4-6`	Claude Sonnet 4.6
`claude-haiku-4-5-20251001`	Claude Haiku 4.5
`claude-sonnet-4-5-20250929`	Claude Sonnet 4.5
`claude-sonnet-4-20250514`	Claude Sonnet 4
`claude-opus-4-1-20250805`	Claude Opus 4.1

Database tables

This module owns no tables. All conversation and usage state is stored in the engine's tables (melis_ai_conversation_state, melis_ai_daily_usage).

Key files

Concern	Path
Provider service	`vendor/melisplatform/melis-ai-engine-claude/src/Service/MelisAIEngineModelClaudeService.php`
Service factory	`vendor/melisplatform/melis-ai-engine-claude/src/Service/Factory/MelisAIEngineModelClaudeServiceFactory.php`
Config block	`vendor/melisplatform/melis-ai-engine-claude/config/app.interface.php`

MelisAIEngineClaude ​

Purpose ​

Role in the React back-office ​

Enable it ​

Key services ​

Tool / function-calling ​

Configuration ​

Seeded models ​

Database tables ​

Key files ​

See also ​