Added comprehensive Watson X model support including:
- IBM Granite models (granite-4-h-small, granite-3-3-8b-instruct, granite-guardian variants, granite-vision, granite-ttm time series models)
- Meta Llama models (llama-3-2-1b/3b/11b-vision/90b-vision, llama-3-3-70b, llama-4-maverick-17b, llama-guard-3-11b-vision)
- Mistral models (mistral-medium-2505, mistral-small-2503, pixtral-12b-2409)
- Additional models (BigScience mt0-xxl-13b, Google flan-t5-xl-3b, OpenAI gpt-oss-120b, SDAIA allam-1-13b-instruct, Core42 jais-13b-chat)
All models include proper pricing, token limits, and capability flags (function calling, vision support, etc.) based on IBM Watson X documentation.
simplifies handleCreate function for CreateKeyModal
moved hooks, components, files where I want them
moved virtual-key page to (console) for common layout
added layout for refactored console file structure, sidebar
wired teams to refactored components
fixing type issue
wired new top level hook useAuthorized
Adds routing to unrefactored pages
Update leftnav.tsx
Update useAuthorized.ts
useAuthorized in virtual-keys/page and deprecation notices
prelim VirtualKeyViewPage, removed old comment
Delete page.tsx
* perf(router): add model_name index for O(1) deployment lookups
Add model_name_to_deployment_indices mapping to optimize _get_all_deployments()
from O(n) to O(1) + O(k) lookups.
- Add model_name_to_deployment_indices: Dict[str, List[int]]
- Add _build_model_name_index() to build/maintain the index
- Update _add_model_to_list_and_index_map() to maintain both indices
- Refactor to use idx = len(self.model_list) before append (cleaner)
- Optimize _get_all_deployments() to use index instead of linear scan
* test(router): add test coverage for _build_model_name_index
Add single comprehensive test for _build_model_name_index() function to fix
code coverage CI failure.
The test verifies:
- Index correctly maps model_name to deployment indices
- Handles multiple deployments per model_name
- Clears and rebuilds index correctly
Fixes: CI code coverage error for _build_model_name_index
Add support for function calling (tools) with Snowflake Cortex models that support it (e.g., Claude 3.5 Sonnet).
Changes:
- Add 'tools' and 'tool_choice' to supported OpenAI parameters
- Implement request transformation: OpenAI function format → Snowflake tool_spec format
- Implement response transformation: Snowflake content_list with tool_use → OpenAI tool_calls
- Add tool_choice transformation: OpenAI nested format → Snowflake array format
Request transformation:
- Transform tools from nested {"type": "function", "function": {...}} to Snowflake's {"tool_spec": {"type": "generic", "name": "...", "input_schema": {...}}}
- Transform tool_choice from {"type": "function", "function": {"name": "..."}} to {"type": "tool", "name": ["..."]}
Response transformation:
- Parse Snowflake's content_list array containing tool_use objects
- Extract tool calls with tool_use_id, name, and input
- Convert to OpenAI's tool_calls format with proper JSON serialization
Testing:
- Add 7 unit tests covering request/response transformations
- Add integration test for Responses API with tool calling
- All tests passing
Fixes issue #15218🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude <noreply@anthropic.com>
