feat(oracle): Add Oracle GenAI Provider with full model family support

[fede-kamel]

Summary

This PR adds comprehensive support for Oracle Cloud Infrastructure (OCI) Generative AI as a provider in the Portkey Gateway. As an Oracle engineer working on GenAI integrations, I've implemented this to bring Portkey's API gateway capabilities to the full range of models available on OCI GenAI.

Key Features

• OCI Signature Authentication: Full support for OCI API key authentication with request signing
• Multi-model family support: Meta Llama, Google Gemini, OpenAI GPT (4o, 5, OSS), xAI Grok, and Cohere models
• Embeddings support: Cohere embedding models with all input types
• Streaming: Full SSE streaming support for all chat models
• Tool/Function calling: Both sync and streaming tool calls, including parallel tool calling
• Model-specific handling: Automatic parameter adjustments for different model families

Supported Features by Model Family

Feature	Meta Llama	Google Gemini	OpenAI GPT-4o	OpenAI GPT-5	OpenAI GPT-OSS	xAI Grok	Cohere
Basic Chat	✅	✅	✅	✅	✅	✅	✅
System Messages	✅	✅	✅	✅	✅	✅	✅
Multi-turn	✅	✅	✅	✅	✅	✅	✅
Streaming	✅	✅	✅	✅	✅	✅	✅
Tool Calling	✅	✅	✅	✅	✅	✅	✅
Tool Streaming	✅	✅	✅	✅	✅	✅	✅
Parallel Tools	✅	✅	✅	✅	✅	✅	✅
Embeddings	-	-	-	-	-	-	✅

Model-Specific Configurations

Model Family	Min Tokens	Uses Reasoning Tokens	Special Parameters
meta.llama	50	No	-
google.gemini	100	Yes	-
openai.gpt-4o	100	No	-
openai.gpt-5	500	Yes	maxCompletionTokens
openai.gpt-oss	200	Yes	reasoningContent
xai.grok	50	No	-
xai.grok-*-reasoning	100	Yes	-
cohere.command	50	No	-

Backwards Compatibility

Gateway Core (Shared Files)

File	Change	Status
jest.config.js	Added ts-jest config	✅ Tests pass, pre-existing failures unrelated
src/providers/open-ai-base/index.ts	Default value logic	✅ All OpenAI-based provider tests pass
src/types/requestBody.ts	Added optional fields	✅ Additive only, no breaking change
src/utils/env.ts	Module loading fix	✅ TypeScript compiles cleanly

Oracle Provider

Change	Type	Impact
Added embed endpoint	Additive	None - new feature
Added model handlers	Additive	None - internal
Added modelConfig.ts	Additive	None - internal
Enhanced content types	Additive	None - existing types still work
GPT-5 maxCompletionTokens	Auto-detect	None - transparent to users
Tool call streaming state	Internal	None - better reliability
reasoningContent handling	Enhancement	None - fixes empty responses

Existing Oracle users will NOT experience breaking changes. All existing functionality continues to work.

Test Coverage

Unit Tests (61 passing)

• modelConfig.test.ts - Model configuration and helpers
• chatComplete.test.ts - Request/response transforms

Integration Tests (Real API calls)

Feature	Unit Tests	Integration Tests	Models Verified
Basic Chat	✅	✅	Llama, Gemini, Grok, GPT-4o, GPT-5, GPT-OSS
System Messages	✅	✅	All models
Multi-turn	✅	✅	All models
Streaming	✅	✅	All models
Tool Calling	✅	✅	All models
Tool Streaming	✅	✅	All models
Parallel Tools	✅	✅	All models (3 tools simultaneously)
Embeddings	✅	✅	9 Cohere models
Error Handling	✅	✅	Invalid model tests
GPT-5 maxCompletionTokens	✅	✅	GPT-5
reasoningContent	✅	✅	GPT-OSS

Parallel Tool Calling Results

Model	Result
meta.llama-4-maverick	✅ 3 tools in parallel
google.gemini-2.5-flash	✅ 3 tools in parallel
xai.grok-3-mini	✅ 3 tools in parallel
openai.gpt-4o	✅ 3 tools in parallel
openai.gpt-5	✅ 3 tools in parallel

Technical Implementation

Files Added/Modified

• src/providers/oracle/ - Complete provider implementation
  • chatComplete.ts - Chat completions with OpenAI-compatible transforms
  • embed.ts - Embeddings support for Cohere models
  • modelConfig.ts - Model family configurations and helpers
  • utils.ts - OCI request signing utilities
  • handlers/ - Model-specific handler classes
  • types/ - TypeScript type definitions

Authentication

The provider uses OCI API Key authentication with request signing:

// Required headers
x-portkey-oracle-tenancy: <tenancy-ocid>
x-portkey-oracle-user: <user-ocid>
x-portkey-oracle-fingerprint: <api-key-fingerprint>
x-portkey-oracle-private-key: <pem-private-key>
x-portkey-oracle-compartment-id: <compartment-ocid>
x-portkey-oracle-region: <region> // e.g., us-chicago-1, eu-frankfurt-1

Verification Checklist

• TypeScript compilation passes
• Prettier formatting passes
• Unit tests pass (61/61)
• Integration tests verified with real API calls
• All model families tested
• Backwards compatibility confirmed
• No breaking changes to existing functionality

[fede-kamel]

Note on src/providers/open-ai-base/index.ts change

While working on the Oracle provider, I ran tsc --noEmit to verify type safety and discovered a pre-existing TypeScript error in open-ai-base/index.ts:

src/providers/open-ai-base/index.ts(72,23): error TS2339: Property 'default' does not exist on type 'ParameterConfig | ParameterConfig[]'.

This error existed on main before my changes. The code works at runtime (JavaScript ignores types), but TypeScript couldn't properly narrow the union type when accessing via index.

Original code:

if (Object.hasOwn(baseParams, key) && !Array.isArray(baseParams[key])) {
  baseParams[key].default = defaultValues?.[key];  // TS error
}

Fixed code:

const param = baseParams[key];
if (param && !Array.isArray(param)) {
  (param as { default?: any }).default = defaultValues?.[key];  // ✅
}

I included this fix since I was already touching the codebase and it improves type safety. If you prefer, I can revert this change and keep it Oracle-only.

[fede-kamel]

Issue Discovery: OCI Streaming Tool Calls

While testing portkey-strands (Strands Agents SDK integration with Portkey), I discovered a critical issue with OCI GenAI streaming responses for tool/function calling.

The Problem

When using OCI GenAI models through the current production Portkey gateway, streaming responses do not properly return tool call data. The model indicates it wants to call a tool (finish_reason: "tool_calls"), but the actual tool call information (function name, arguments) is missing from the streamed chunks.

Test Results (before this PR):

Provider	Model	Basic Chat	Tool Use
OpenAI	gpt-4o	✅ Pass	✅ Pass
Anthropic	claude-sonnet-4-6	✅ Pass	✅ Pass
OCI	meta.llama-3.3-70b	✅ Pass	✅ Pass
OCI	xai.grok-4-1-fast-reasoning	✅ Pass	✅ Passl
OCI	cohere.command-a	✅ Pass

Actual Error

# Model returns end_turn with empty content instead of tool_use
AgentResult(
    stop_reason='end_turn',  # Should be 'tool_use'
    message={'role': 'assistant', 'content': []},  # Tool call data missing
    ...
)

The streaming response returns stopReason: 'end_turn' instead of 'tool_use', and the contentBlockStart events for tool calls are never emitted.

Why This PR Fixes It

This PR includes proper streaming state management for tool calls:

1. Tool call accumulation - Properly buffers tool call chunks across SSE events
2. Index tracking - Maintains tool call indices for parallel tool calls
3. Finish reason mapping - Correctly maps OCI's finish reasons to OpenAI-compatible format
4. Content block emission - Emits proper contentBlockStart/contentBlockDelta/contentBlockStop events for tools

Verification

After applying this PR's changes, all OCI models pass tool calling tests:

• Single tool calls
• Multiple sequential tools
• Parallel tool calls (3+ simultaneous)
• Streaming tool calls

This enables full agentic workflows with OCI GenAI models through Portkey.

[fede-kamel]

cc @VisargD - This PR addresses a critical issue affecting agentic workflows with OCI GenAI models. The streaming tool call bug prevents Strands Agents (and likely other agent frameworks) from working properly with OCI models through Portkey.

Would appreciate a review when you have time!

[fede-kamel]

Tracking issue created: #1538

This documents the critical streaming tool call bug and explains why keeping the Oracle GenAI integration up to date is important for enterprise customers.

[fede-kamel]

Rebased check done: branch is already up to date with main (no conflicts).

Validation run:

• Unit: tests/unit/src/providers/oracle/chatComplete.test.ts, tests/unit/src/providers/oracle/modelConfig.test.ts (PASS)
• Integration (OCI profile LUIGI_FRA_API): tests/integration/src/providers/oracle/run-tests.sh ... all (PASS; chat+embed suites)

Re-pinging for review.

[fede-kamel]

Friendly follow-up on this one when you have a moment: @VisargD @narengogi\n\nWould appreciate a review. Thank you!

[fede-kamel]

@narengogi @VisargD

Maintainer note: keeping OCI support current is strategically important here, not just additive. OCI is increasingly exposing new model families and provider-specific behaviors behind a single enterprise surface, and that surface changes fast: model availability, request/response shapes, auth expectations, token parameters, streaming/tool-call behavior, and embedding support all evolve over time.

If the OCI provider lags, Portkey users in Oracle environments end up with capability gaps or subtle incompatibilities even when the same models are available elsewhere. Keeping OCI up to date means Portkey stays credible as a gateway layer for Oracle-hosted GPT/Gemini/Llama/Grok/Cohere workloads, reduces integration drift for enterprise customers, and avoids pushing teams into provider-specific forks or direct OCI workarounds.

This PR moves OCI much closer to parity with the broader provider matrix, which is exactly the kind of maintenance surface that compounds in value if it is kept current.

[fede-kamel]

Hey @VisargD @narengogi — friendly ping on this one. It's been open for about 3 weeks now.

Beyond the technical additions (full OCI GenAI support, streaming tool call fix, 61 unit tests), there's a broader Portkey + Oracle partnership story here: Portkey becomes the gateway layer for enterprise teams running GenAI on OCI, and Oracle customers get unified API access to all their OCI-hosted models (Llama, Gemini, GPT, Grok, Cohere) through a gateway they may already be using for OpenAI/Anthropic.

That's a compelling value prop for both sides — Portkey expands its enterprise reach, Oracle gets first-class representation in the provider matrix.

Happy to jump on a call if it's easier to walk through the implementation. Would really appreciate a review when you get a chance!