UNPKG

comfyui-mcp

Version:

Local-first, agent-native control plane for ComfyUI — MCP server + autonomous sidebar agent that drives your live graph in natural language on ANY LLM: Claude/ChatGPT/Gemini on your subscription (no API key), free local models via Ollama (fully offline),

132 lines • 7.14 kB
// Agent backend port — the provider-neutral seam that lets the panel orchestrator // run on different agent providers (Claude Agent SDK today, OpenAI Codex next) via // dependency injection. See docs/design/agent-backend-injection.md. // // PanelAgent keeps the orchestration (queue, turn-gate, bridge push, rewind-anchor // tracking, self-restart) and delegates the provider-specific bits — opening a // session, normalizing the provider's message stream to canonical AgentEvents, // interrupt, model enumeration, session resume/fork — to an injected AgentBackend. /** Capability descriptor for the Claude Agent SDK backend. */ export const CLAUDE_CAPABILITIES = { persistentChannel: true, streamingDeltas: true, interruptMidTurn: true, forkAtAnchor: true, inProcessMcp: true, modelEnumeration: true, slashCommands: true, hooks: true, vision: true, // resolves image refs to inline base64 blocks (shapeTurn) }; /** Capability descriptor for the Codex app-server backend (Phase 2). */ export const CODEX_CAPABILITIES = { persistentChannel: true, // thread + turn/start (resume by threadId) streamingDeltas: true, interruptMidTurn: true, // turn/interrupt forkAtAnchor: false, // thread/resume is whole-thread only (for now) inProcessMcp: false, // config-declared MCP servers only modelEnumeration: true, // config/read slashCommands: false, hooks: false, vision: true, // gpt-5.5 sees images; delivered as `localImage` turn input items }; /** Capability descriptor for the Gemini CLI ACP backend (Agent Client Protocol). * Mirrors the Codex posture: a persistent session over a JSON-RPC-over-stdio * client, streaming deltas + tool calls, interrupt via `session/cancel`, and * config-declared MCP servers (no in-process SDK MCP). forkAtAnchor is false — * ACP `session/load` is whole-session only, with no per-turn rewind anchor. */ export const GEMINI_CAPABILITIES = { persistentChannel: true, // session/new + repeated session/prompt streamingDeltas: true, // session/update agent_message_chunk / agent_thought_chunk interruptMidTurn: true, // session/cancel forkAtAnchor: false, // session/load is whole-session only (no anchor fork) inProcessMcp: false, // ACP session/new declares config MCP servers only modelEnumeration: true, // static catalog (gemini-2.5-pro / -flash) — ACP exposes no catalog slashCommands: false, hooks: false, vision: true, // gemini-2.5 sees images; delivered as inline base64 image ContentBlocks }; /** Capability descriptor for the Antigravity CLI backend (`agy`, issue #262) — * Google's official replacement for the individual-tier Gemini CLI subscription * path (Google AI Pro/Ultra). `agy` exposes no machine-readable event protocol, * only plain-text `-p` print mode + `--continue` conversation continuity — so * this is a spawn-per-turn adapter with honestly reduced capabilities: * streamingDeltas=true is the CLI's own progressive stdout (final answer text * only, no structured tool events), and vision=false (no documented -p image * input). Models come LIVE from `agy models` (no static catalog). */ export const ANTIGRAVITY_CAPABILITIES = { persistentChannel: true, // spawn-per-turn, continuity via `agy --continue` streamingDeltas: true, // progressive stdout of the final answer interruptMidTurn: true, // kill the in-flight child tree; next turn continues forkAtAnchor: false, // agy owns conversation storage; no per-turn anchor inProcessMcp: false, // workspace .agents/mcp_config.json only modelEnumeration: true, // `agy models` (live account catalog) slashCommands: false, hooks: false, vision: false, // no documented image input in -p mode }; /** Capability descriptor for the Grok CLI ACP backend (xAI / Grok Build). * Same ACP posture as Gemini: persistent session, streaming deltas, interrupt, * config-declared MCP servers, static model catalog at spawn. */ export const GROK_CAPABILITIES = { persistentChannel: true, streamingDeltas: true, interruptMidTurn: true, forkAtAnchor: false, inProcessMcp: false, modelEnumeration: true, // grok-composer-2.5-fast / grok-build — ACP exposes no catalog slashCommands: false, hooks: false, vision: true, }; /** Capability descriptor for the Ollama local-LLM backend (issue #97's panel * phase). Ollama is a stateless HTTP daemon, so the backend owns the whole * agentic loop itself (stream /api/chat, dispatch tool calls, repeat) and * keeps the conversation history in-memory — persistentChannel is true from * the panel's perspective, but forkAtAnchor is out. Vision is true at the * BACKEND level: whether images are actually understood is a per-MODEL * property (gemma4 sees them, qwen3 doesn't; DeepSeek's API rejects them), so * the backend always attempts delivery and degrades gracefully — an endpoint * that rejects image input gets one retry with images stripped and an honest * note to both the user and the model. */ export const OLLAMA_CAPABILITIES = { persistentChannel: true, // in-memory history + repeated /api/chat streamingDeltas: true, // NDJSON chunk stream interruptMidTurn: true, // AbortController on the in-flight fetch forkAtAnchor: false, inProcessMcp: false, // MCP clients internally; the model sees the 6-tool router modelEnumeration: true, // GET /api/tags (locally pulled models) slashCommands: false, hooks: false, vision: true, // attempted for every model; graceful strip-and-retry on rejection }; /** ChatGPT subscription via direct Codex OAuth (~/.codex/auth.json) — Codex Responses * HTTP backend (not the codex app-server CLI). Same 6-tool router as Ollama. */ export const CHATGPT_CAPABILITIES = { persistentChannel: true, streamingDeltas: true, interruptMidTurn: true, forkAtAnchor: false, inProcessMcp: false, modelEnumeration: true, // ~/.codex/models_cache.json + configured default slashCommands: false, hooks: false, vision: true, // Responses input_image data URLs; strip-and-retry on rejection (#218) }; /** Kimi Code subscription OAuth or KIMI_API_KEY — OpenAI-compatible coding API. */ export const KIMI_CAPABILITIES = { ...OLLAMA_CAPABILITIES, }; // NOTE: glm/moonshot no longer need dedicated *_CAPABILITIES consts — the generic // api-key factory (services/openai-provider-registry + makeOpenAiKeyBackend in // orchestrator/index.ts) builds a plain OllamaBackend, which already reports // OLLAMA_CAPABILITIES (the value the old GLM_CAPABILITIES/MOONSHOT_CAPABILITIES // spreads carried). Their BackendId union members are retained above. /** GitHub Copilot chat via in-panel device-code OAuth — EXPERIMENTAL (ToS risk, * see OAUTH_PROVIDERS.copilot). OpenAI-compatible chat/completions + the same * 6-tool router as Ollama/GLM/Kimi. The exact contract (endpoints, headers) is * UNVERIFIED offline — see copilot-backend.ts's module doc. */ export const COPILOT_CAPABILITIES = { ...OLLAMA_CAPABILITIES, }; //# sourceMappingURL=agent-backend.js.map