chore: regenerate API specs and update provider compatibility matrix

Author: robinnarsinghranabhat

docs/docs/api-openai/conformance.mdx

@@ -27,7 +27,7 @@ This documentation is auto-generated from the OpenAI API specification compariso
 
 ## Integration Test Coverage
 
-Overall Test Coverage Score: 44.1%
+Overall Test Coverage Score: 45.0%
 
 | Category | Covered | Total | Score |
 |----------|---------|-------|-------|
@@ -36,7 +36,7 @@ Overall Test Coverage Score: 44.1%
 | Request Parameters | 21 | 25 | 84.0% |
 | Streaming Events | 16 | 53 | 30.2% |
 | Structured Output | 0 | 2 | 0.0% |
-| Tools | 2 | 16 | 12.5% |
+| Tools | 3 | 16 | 18.8% |
 
 ## Category Scores
 

docs/docs/api-openai/provider_matrix.md

@@ -21,8 +21,8 @@ inference provider, based on integration test results.
 |----------|--------|---------|---------|----------|
 | azure | 102 | 102 | 0 | 84% |
 | bedrock | 27 | 27 | 0 | 22% |
-| ollama | 2 | 2 | 0 | 2% |
-| openai | 121 | 121 | 0 | 100% |
+| ollama | 4 | 4 | 0 | 3% |
+| openai | 121 | 121 | 0 | 99% |
 | vllm | 3 | 3 | 0 | 2% |
 | watsonx | 56 | 56 | 0 | 46% |
 
@@ -34,7 +34,7 @@ Models, endpoints, and versions used during test recordings.
 |----------|----------|----------|--------------|
 | azure | gpt-4o | llama-stack-test.openai.azure.com, lls-test.openai.azure.com | openai sdk: 2.5.0 |
 | bedrock | openai.gpt-oss-20b | bedrock-mantle.us-east-2.api.aws, bedrock-mantle.us-west-2.api.aws | openai sdk: 2.5.0 |
-| ollama | gpt-oss:20b | — | openai sdk: 2.5.0, vllm server: 0.9.2rc2.dev136+g0b382b53a.d20250924 |
+| ollama | gpt-oss:20b | — | openai sdk: 2.5.0, vllm server: 0.17.2rc1.dev79+g5ce2d10e4 |
 | openai | gpt-4o, o4-mini, text-embedding-3-small | api.openai.com | openai sdk: 2.5.0 |
 | vllm | Qwen/Qwen3-0.6B | — | openai sdk: 2.5.0, vllm server: 0.18.1rc1.dev197+g0e9358c11 |
 | watsonx | meta-llama/llama-3-3-70b-instruct | us-south.ml.cloud.ibm.com | openai sdk: 2.5.0 |
@@ -148,8 +148,9 @@ Models, endpoints, and versions used during test recordings.
 
 | Feature | azure | bedrock | ollama | openai | vllm | watsonx |
 | --- | --- | --- | --- | --- | --- | --- |
-| reasoning basic streaming | ✅ | ✅ | ⏭️ | ✅ | ✅ | ✅ |
+| reasoning basic streaming | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | reasoning multi turn passthrough | ⏭️ | ✅ | ✅ | ✅ | ✅ | ⏭️ |
+| reasoning multi turn with tool call | ⏭️ | ⏭️ | ✅ | ⏭️ | ⏭️ | ⏭️ |
 | reasoning non streaming | ⏭️ | ✅ | ✅ | ✅ | ✅ | ⏭️ |
 
 ## Responses Access Control

src/llama_stack_api/inference/api.py

@@ -17,7 +17,6 @@
     OpenAIChatCompletionChunk,
     OpenAIChatCompletionChunkWithReasoning,
     OpenAIChatCompletionRequestWithExtraBody,
-    OpenAIChatCompletionWithReasoning,
     OpenAICompletion,
     OpenAICompletionRequestWithExtraBody,
     OpenAICompletionWithInputMessages,

tests/integration/responses/test_reasoning.py

@@ -30,7 +30,7 @@ def provider_from_model(client_with_models, text_model_id):
 
 def skip_if_reasoning_content_not_provided(client_with_models, text_model_id):
     provider_type = provider_from_model(client_with_models, text_model_id).provider_type
-    if provider_type in ("remote::openai", "remote::azure", "remote::watsonx", "remote::vllm"):
+    if provider_type in ("remote::openai", "remote::azure", "remote::watsonx"):
         pytest.skip(f"{provider_type} doesn't return reasoning content.")