feat: add Requesty adapter (OpenAI-compatible)

Signed-off-by: Thibault Jaigu <thibault.jaigu@gmail.com>

Author: Thibaultjaigu

README.md

@@ -39,6 +39,7 @@ All agents now use a **standardized interaction pattern** with structured three-
 - ✅ **Kimi** (Moonshot AI) - Interactive AI agent with advanced reasoning (interactive-first CLI)
 - ✅ **OpenCode** (SST) - AI coding agent built for the terminal (non-interactive run mode)
 - ✅ **OpenRouter** - Unified API access to 400+ models from multiple providers (API-based, no CLI required) 🌐 **API-based**
+- ✅ **Requesty** - OpenAI-compatible gateway with access to 400+ models from multiple providers (API-based, no CLI required) 🌐 **API-based**
 - ✅ **Qoder** - Agentic coding platform with enhanced context engineering
 - ✅ **Qwen** (Alibaba) - Multilingual capabilities
 - ✅ **Ollama** - Local LLM support (planned)
@@ -317,6 +318,7 @@ AgentPipe supports three formats for specifying agents via the `--agents` / `-a`
 | `groq` | ✅ Optional | No | `llama3-70b`, `mixtral-8x7b` |
 | `crush` | ✅ Optional | No | `deepseek-r1`, `qwen-2.5` |
 | `openrouter` | ✅ **Required** | Yes | `anthropic/claude-sonnet-4-5`, `google/gemini-2.5-pro` |
+| `requesty` | ✅ **Required** | Yes | `openai/gpt-4o-mini`, `anthropic/claude-sonnet-4-5` |
 | `kimi` | ❌ Not supported | No | N/A |
 | `cursor` | ❌ Not supported | No | N/A |
 | `amp` | ❌ Not supported | No | N/A |

cmd/model_validation.go

@@ -59,6 +59,10 @@ var agentModelSupport = map[string]ModelSupport{
 		Supported: true,
 		Required:  true,
 	},
+	"requesty": {
+		Supported: true,
+		Required:  true,
+	},
 
 	// CLI agents without --model support
 	"kimi": {

examples/requesty-conversation.yaml

@@ -0,0 +1,53 @@
+version: "1.0"
+
+# Requesty Multi-Agent Conversation Example
+#
+# This example demonstrates using Requesty's unified, OpenAI-compatible API to
+# access multiple AI models from different providers in a single conversation.
+#
+# Requirements:
+#   - Set REQUESTY_API_KEY environment variable
+#   - Requesty account with credits (https://requesty.ai)
+#
+# Run with:
+#   export REQUESTY_API_KEY=your-key-here
+#   agentpipe run -c examples/requesty-conversation.yaml
+
+agents:
+  - id: claude-via-requesty
+    type: requesty
+    name: "Claude (Requesty)"
+    prompt: "You are Claude, an AI assistant created by Anthropic. You are thoughtful, analytical, and enjoy deep discussions."
+    announcement: "🤖 Claude has joined via Requesty API!"
+    model: anthropic/claude-sonnet-4-5
+    temperature: 0.7
+    max_tokens: 500
+
+  - id: gemini-via-requesty
+    type: requesty
+    name: "Gemini (Requesty)"
+    prompt: "You are Gemini, Google's AI assistant. You are curious, factual, and love to explore new ideas."
+    announcement: "✨ Gemini has joined via Requesty API!"
+    model: google/gemini-2.5-flash
+    temperature: 0.6
+    max_tokens: 500
+
+  - id: gpt-via-requesty
+    type: requesty
+    name: "GPT (Requesty)"
+    prompt: "You are GPT, OpenAI's language model. You are helpful, creative, and enjoy collaborative problem-solving."
+    announcement: "🧠 GPT has joined via Requesty API!"
+    model: openai/gpt-4o-mini
+    temperature: 0.8
+    max_tokens: 500
+
+orchestrator:
+  mode: round-robin
+  max_turns: 8
+  turn_timeout: 30s
+  response_delay: 2s
+  initial_prompt: "Let's have a discussion about the future of AI and its impact on society. Each of you represents a different AI platform - what unique perspectives do you bring to this topic?"
+
+logging:
+  enabled: true
+  show_metrics: true

examples/requesty-solo.yaml

@@ -0,0 +1,36 @@
+version: "1.0"
+
+# Requesty Solo Agent Example
+#
+# This example shows how to use a single Requesty agent for a conversation.
+# This is useful for testing or when you want to use a specific model via API
+# without installing its CLI tool.
+#
+# Requirements:
+#   - Set REQUESTY_API_KEY environment variable
+#   - Requesty account with credits (https://requesty.ai)
+#
+# Run with:
+#   export REQUESTY_API_KEY=your-key-here
+#   agentpipe run -c examples/requesty-solo.yaml
+
+agents:
+  - id: gpt-via-requesty
+    type: requesty
+    name: "GPT (Requesty)"
+    prompt: "You are a powerful reasoning assistant. When solving problems, break down your thinking step by step and show your reasoning process clearly."
+    announcement: "🧪 GPT has joined via Requesty API!"
+    model: openai/gpt-4o-mini
+    temperature: 0.5
+    max_tokens: 2000
+
+orchestrator:
+  mode: round-robin
+  max_turns: 3
+  turn_timeout: 60s
+  response_delay: 1s
+  initial_prompt: "Solve this logic puzzle: You have 12 balls that look identical. One ball is slightly heavier or lighter than the others. Using a balance scale only 3 times, how can you identify which ball is different and whether it's heavier or lighter?"
+
+logging:
+  enabled: true
+  show_metrics: true

internal/providers/providers.json

@@ -3458,6 +3458,57 @@
         }
       ]
     },
+    {
+      "name": "Requesty",
+      "id": "requesty",
+      "type": "openai",
+      "api_key": "$REQUESTY_API_KEY",
+      "api_endpoint": "https://router.requesty.ai/v1",
+      "default_large_model_id": "anthropic/claude-sonnet-4-5",
+      "default_small_model_id": "openai/gpt-4o-mini",
+      "models": [
+        {
+          "id": "openai/gpt-4o-mini",
+          "name": "OpenAI: GPT-4o mini",
+          "cost_per_1m_in": 0.15,
+          "cost_per_1m_out": 0.6,
+          "context_window": 128000,
+          "default_max_tokens": 4096,
+          "can_reason": false,
+          "supports_attachments": true
+        },
+        {
+          "id": "openai/gpt-4o",
+          "name": "OpenAI: GPT-4o",
+          "cost_per_1m_in": 2.5,
+          "cost_per_1m_out": 10,
+          "context_window": 128000,
+          "default_max_tokens": 4096,
+          "can_reason": false,
+          "supports_attachments": true
+        },
+        {
+          "id": "anthropic/claude-sonnet-4-5",
+          "name": "Anthropic: Claude Sonnet 4.5",
+          "cost_per_1m_in": 3,
+          "cost_per_1m_out": 15,
+          "context_window": 200000,
+          "default_max_tokens": 8192,
+          "can_reason": true,
+          "supports_attachments": true
+        },
+        {
+          "id": "google/gemini-2.5-flash",
+          "name": "Google: Gemini 2.5 Flash",
+          "cost_per_1m_in": 0.3,
+          "cost_per_1m_out": 2.5,
+          "context_window": 1048576,
+          "default_max_tokens": 8192,
+          "can_reason": true,
+          "supports_attachments": true
+        }
+      ]
+    },
     {
       "name": "Venice AI",
       "id": "venice",
@@ -3663,4 +3714,4 @@
       ]
     }
   ]
-}
+}