feat: Adding portkey.ai gateway as a custom model

This PR adds first-class support for **Portkey**, a gateway platform for LLM providers, into the Strands SDK. It enables a unified, configurable, and extensible way to interact with multiple AI models (OpenAI, Anthropic via Bedrock, Gemini, and more) through a single abstraction.

The integration emphasizes **tool use** and **streaming completions**, and lays foundational support for future capabilities like **multi-modal interactions** (images, audio — coming in a future PR).

---

[Portkey](https://portkey.ai) is a powerful LLM gateway that provides:

- **Unified API access** to multiple model providers
- **Smart routing** based on performance, reliability, or cost
- **Built-in observability** and analytics (latency, usage)
- **Retry, fallback, and caching strategies**
- **Key and model management** for dynamic overrides

Portkey is becoming the go-to model abstraction layer for companies scaling LLM usage — including Notion, Descript, Ramp, and others — because it makes managing model complexity simple, modular, and scalable.

---

This integration supports and has been tested with:

- **OpenAI** (GPT-4, GPT-3.5)
- **Anthropic**, via **Amazon Bedrock**
- **Amazon Bedrock-native models**
- **Google Gemini**
- **Other providers** supported by Portkey configuration

- **Tool Use capabilities** for:
  - OpenAI (native function-calling support)
  - Anthropic (via Bedrock with partial support)

---

Adding Portkey unlocks significant benefits:

| Benefit | Description |
|--------|-------------|
| **Model Agility** | Swap providers without changing SDK logic |
| **Unified Tooling** | Consistent handling of `tool_calls` across models |
| **Resilience** | Add retries, rate limits, and observability |
| **Flexibility** | Customize parameters like temperature, tokens, and stream |
| **Cost Optimization** | Route to cheaper models or fallback options |

---

Portkey is not just a convenience — it is a **requirement** for SDK adoption in many real-world AI systems.

Leading companies already standardize on Portkey. Without first-class support, **these companies cannot use the SDK**, as their LLM access, observability, and governance are fully routed through Portkey.

- **Notion** – internal AI copilots with dynamic routing
- **Ramp** – cost-based model fallback and observability
- **Descript** – creative workflows across providers
- **Puzzle**, **DeepOpinion**, and other AI-first orgs

📎 **Reference**: [Portkey Customers](https://www.portkey.ai/customers)

Supporting Portkey makes the Strands SDK **immediately compatible** with the infrastructure already powering major AI systems — greatly reducing integration effort.

---

This implementation extends the `Model` interface within the **Strands SDK**, Amazon’s agent platform for intelligent task automation.

- ✅ Streaming responses
- ✅ Tool calling (`tool_calls` / `tool_use`)
- ✅ System prompt injection
- ✅ Token configuration per model
- ✅ Model-agnostic formatting of inputs/outputs

> 🧠 **Coming Soon**: In a follow-up PR, we will add **multi-modal capabilities** (images and audio input), further expanding the power of Strands agents to handle rich sensory data.

---

This PR introduces a new model provider class:

- `PortkeyModel`, implementing the full `Model` interface
- Handles provider-specific tool use behavior (OpenAI vs Bedrock)
- Formats and streams messages with structured deltas
- Manages tool call life cycle: initiation, input, completion
- Defensive checks for context window and malformed payloads
- Full support for `ToolSpec` mapping and schema encoding

All logic is structured to allow future expansion to other Portkey-supported capabilities (e.g., caching, retry policies, routing rules).

---

This feature was validated across the following dimensions:

- ✔️ Basic chat completions
- ✔️ Streaming token responses
- ✔️ Tool calling with input parameters
- ✔️ Tool result handoff
- ✔️ Multiple model backends:
  - OpenAI GPT-4 (tools)
  - Anthropic Claude (via Bedrock)
  - Gemini (streaming + simple use)
  - Bedrock-native (Jurassic, Titan)

---

- [ ] Add multi-modal support (images, audio)
- [ ] Integrate Portkey usage metrics into internal observability stack
- [ ] Add routing and fallback policies via Portkey configuration
- [ ] Enable A/B experimentation between providers at runtime

---

- [Portkey.ai Documentation](https://docs.portkey.ai/)
- [Portkey Customer Base](https://www.portkey.ai/customers)
- [Amazon Bedrock Overview](https://docs.aws.amazon.com/bedrock/)
- [OpenAI Function Calling](https://platform.openai.com/docs/guides/function-calling)
- [Strands SDK](https://github.com/aws/strands-sdk)

---

feat: Adding portkey.ai gateway as a custom model

feat: Adding portkey.ai gateway as a custom model

feat: Adding portkey.ai gateway as a custom model

feat: Adding portkey.ai gateway as a custom model

Author: Fede Kamelhar

README.md

@@ -118,6 +118,7 @@ from strands import Agent
 from strands.models import BedrockModel
 from strands.models.ollama import OllamaModel
 from strands.models.llamaapi import LlamaAPIModel
+from strands.models.portkey import PortkeyModel
 
 # Bedrock
 bedrock_model = BedrockModel(
@@ -142,6 +143,17 @@ llama_model = LlamaAPIModel(
 )
 agent = Agent(model=llama_model)
 response = agent("Tell me about Agentic AI")
+
+# Portkey for all models
+portkey_model = PortkeyModel(
+    api_key="<PORTKEY_API_KEY>",
+    model_id="anthropic.claude-3-5-sonnet-20241022-v2:0",
+    virtual_key="<BEDROCK_VIRTUAL_KEY>",
+    provider="bedrock",
+    base_url="http://portkey-service-gateway.service.prod.example.com/v1",
+)
+agent = Agent(model=portkey_model)
+response = agent("Tell me about Agentic AI")
 ```
 
 Built-in providers:

pyproject.toml

@@ -50,6 +50,11 @@ packages = ["src/strands"]
 anthropic = [
     "anthropic>=0.21.0,<1.0.0",
 ]
+# Optional dependencies for different AI providers
+portkey = [
+    "portkey-ai>=1.0.0,<2.0.0",
+]
+
 dev = [
     "commitizen>=4.4.0,<5.0.0",
     "hatch>=1.0.0,<2.0.0",
@@ -107,7 +112,7 @@ lint-fix = [
 ]
 
 [tool.hatch.envs.hatch-test]
-features = ["anthropic", "litellm", "llamaapi", "ollama", "openai"]
+features = ["anthropic", "litellm", "llamaapi", "ollama", "openai", "portkey"]
 extra-dependencies = [
     "moto>=5.1.0,<6.0.0",
     "pytest>=8.0.0,<9.0.0",