pre-commit run -a

Author: mattf

docs/docs/api-openai/provider_matrix.md

@@ -19,13 +19,13 @@ inference provider, based on integration test results.
 
 | Provider | Tested | Passing | Failing | Coverage |
 |----------|--------|---------|---------|----------|
-| azure | 111 | 111 | 0 | 81% |
+| azure | 111 | 111 | 0 | 82% |
 | bedrock | 27 | 27 | 0 | 20% |
-| ollama | 4 | 4 | 0 | 3% |
-| openai | 136 | 136 | 0 | 99% |
-| vertexai | 70 | 70 | 0 | 51% |
-| vllm | 4 | 4 | 0 | 3% |
-| watsonx | 61 | 61 | 0 | 44% |
+| ollama | 3 | 3 | 0 | 2% |
+| openai | 136 | 136 | 0 | 100% |
+| vertexai | 70 | 70 | 0 | 52% |
+| vllm | 3 | 3 | 0 | 2% |
+| watsonx | 61 | 61 | 0 | 45% |
 
 ## Provider Details
 
@@ -35,7 +35,7 @@ Models, endpoints, and versions used during test recordings.
 |----------|----------|----------|--------------|
 | azure | gpt-4o | llama-stack-test.openai.azure.com, lls-test.openai.azure.com, ogx-test.openai.azure.com | openai sdk: 2.43.0 |
 | bedrock | openai.gpt-oss-20b-1:0 | bedrock-runtime.us-west-2.amazonaws.com | openai sdk: 2.30.0 |
-| ollama | deepseek-r1:1.5b, gpt-oss:20b | — | openai sdk: 2.43.0, vllm server: 0.17.2rc1.dev79+g5ce2d10e4 |
+| ollama | deepseek-r1:1.5b | — | openai sdk: 2.43.0 |
 | openai | gpt-4o, o4-mini, text-embedding-3-small | api.openai.com | openai sdk: 2.43.0 |
 | vertexai | publishers/google/models/gemini-2.0-flash | — | openai sdk: 2.5.0, provider: vertexai |
 | vllm | Qwen/Qwen3-0.6B | — | openai sdk: 2.5.0, vllm server: 0.17.2rc1.dev79+g5ce2d10e4 |
@@ -167,7 +167,6 @@ Models, endpoints, and versions used during test recordings.
 | --- | --- | --- | --- | --- | --- | --- | --- |
 | reasoning basic streaming | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ | ✅ |
 | reasoning multi turn passthrough | ⏭️ | ✅ | ✅ | ✅ | ⏭️ | ✅ | ✅ |
-| reasoning multi turn with tool call | ⏭️ | ⏭️ | ✅ | ⏭️ | ⏭️ | ✅ | ⏭️ |
 | reasoning no summary without request | ⏭️ | ⏭️ | ⏭️ | ✅ | ⏭️ | ⏭️ | ✅ |
 | reasoning non streaming | ⏭️ | ✅ | ✅ | ✅ | ⏭️ | ✅ | ✅ |
 | reasoning summary event ordering | ⏭️ | ⏭️ | ⏭️ | ✅ | ⏭️ | ⏭️ | ✅ |

tests/integration/TARGET_MODELS.md

@@ -14,15 +14,15 @@ These jobs come from the `default` section of `ci_matrix.json`. They all run in
 | `bedrock` | `bedrock` | library client only; 3 roots |
 | `base` | `ollama-postgres` | server client only; Postgres store |
 | `vision` | `ollama-vision` | `test_vision_inference.py` only |
-| `responses` | `gpt` | `responses` only; Responses coverage: 136/137 (99%) |
-| `responses` | `azure` | `responses` only; Responses coverage: 111/137 (81%) |
-| `gpt-reasoning` | `gpt-reasoning` | 2 roots; Responses coverage: 136/137 (99%) |
-| `responses` | `watsonx` | `responses` only; Responses coverage: 61/137 (45%) |
-| `responses` | `vertexai` | `responses` only; Responses coverage: 70/137 (51%) |
-| `bedrock-responses` | `bedrock` | 6 roots; Responses coverage: 27/137 (20%) |
+| `responses` | `gpt` | `responses` only; Responses coverage: 136/136 (100%) |
+| `responses` | `azure` | `responses` only; Responses coverage: 111/136 (82%) |
+| `gpt-reasoning` | `gpt-reasoning` | 2 roots; Responses coverage: 136/136 (100%) |
+| `responses` | `watsonx` | `responses` only; Responses coverage: 61/136 (45%) |
+| `responses` | `vertexai` | `responses` only; Responses coverage: 70/136 (51%) |
+| `bedrock-responses` | `bedrock` | 6 roots; Responses coverage: 27/136 (20%) |
 | `base-vllm-subset` | `vllm` | `inference` only |
-| `vllm-reasoning` | `vllm` | `test_reasoning.py` only; Responses coverage: 4/137 (3%) |
-| `ollama-reasoning` | `ollama-reasoning` | 5 roots; Responses coverage: 4/137 (3%) |
+| `vllm-reasoning` | `vllm` | `test_reasoning.py` only; Responses coverage: 3/136 (2%) |
+| `ollama-reasoning` | `ollama-reasoning` | 5 roots; Responses coverage: 3/136 (2%) |
 | `messages` | `ollama` | `messages` only |
 | `messages-openai` | `gpt` | `messages` only |
 | `interactions` | `gemini` | `interactions` only |
@@ -75,12 +75,12 @@ This section is derived from the same replay recordings used to generate `docs/d
 
 | Provider | Tested | Passing | Coverage |
 |----------|--------|---------|----------|
-| OpenAI | 136 | 136 | 99% |
-| Azure | 111 | 111 | 81% |
+| OpenAI | 136 | 136 | 100% |
+| Azure | 111 | 111 | 82% |
 | Vertex AI | 70 | 70 | 51% |
 | WatsonX | 61 | 61 | 45% |
 | Bedrock | 27 | 27 | 20% |
-| Ollama | 4 | 4 | 3% |
-| vLLM | 4 | 4 | 3% |
+| Ollama | 3 | 3 | 2% |
+| vLLM | 3 | 3 | 2% |
 
-Total Responses features counted: 137.
+Total Responses features counted: 136.