diff --git a/.github/actions/run-and-record-tests/action.yml b/.github/actions/run-and-record-tests/action.yml
index ec4d7f977..d44cba4ee 100644
--- a/.github/actions/run-and-record-tests/action.yml
+++ b/.github/actions/run-and-record-tests/action.yml
@@ -72,7 +72,8 @@ runs:
echo "New recordings detected, committing and pushing"
git add tests/integration/
- git commit -m "Recordings update from CI (suite: ${{ inputs.suite }})"
+ git commit -m "Recordings update from CI (setup: ${{ inputs.setup }}, suite: ${{ inputs.suite }})"
+
git fetch origin ${{ github.ref_name }}
git rebase origin/${{ github.ref_name }}
echo "Rebased successfully"
@@ -88,6 +89,8 @@ runs:
run: |
# Ollama logs (if ollama container exists)
sudo docker logs ollama > ollama-${{ inputs.inference-mode }}.log 2>&1 || true
+ # vllm logs (if vllm container exists)
+ sudo docker logs vllm > vllm-${{ inputs.inference-mode }}.log 2>&1 || true
# Note: distro container logs are now dumped in integration-tests.sh before container is removed
- name: Upload logs
diff --git a/.github/actions/setup-vllm/action.yml b/.github/actions/setup-vllm/action.yml
index 17ebd42f2..34ced0998 100644
--- a/.github/actions/setup-vllm/action.yml
+++ b/.github/actions/setup-vllm/action.yml
@@ -11,13 +11,14 @@ runs:
--name vllm \
-p 8000:8000 \
--privileged=true \
- quay.io/higginsd/vllm-cpu:65393ee064 \
+ quay.io/higginsd/vllm-cpu:65393ee064-qwen3 \
--host 0.0.0.0 \
--port 8000 \
--enable-auto-tool-choice \
- --tool-call-parser llama3_json \
- --model /root/.cache/Llama-3.2-1B-Instruct \
- --served-model-name meta-llama/Llama-3.2-1B-Instruct
+ --tool-call-parser hermes \
+ --model /root/.cache/Qwen3-0.6B \
+ --served-model-name Qwen/Qwen3-0.6B \
+ --max-model-len 8192
# Wait for vllm to be ready
echo "Waiting for vllm to be ready..."
diff --git a/.github/workflows/integration-tests.yml b/.github/workflows/integration-tests.yml
index 41822fa79..2c797e906 100644
--- a/.github/workflows/integration-tests.yml
+++ b/.github/workflows/integration-tests.yml
@@ -27,7 +27,6 @@ on:
schedule:
# If changing the cron schedule, update the provider in the test-matrix job
- cron: '0 0 * * *' # (test latest client) Daily at 12 AM UTC
- - cron: '1 0 * * 0' # (test vllm) Weekly on Sunday at 1 AM UTC
workflow_dispatch:
inputs:
test-all-client-versions:
diff --git a/scripts/integration-tests.sh b/scripts/integration-tests.sh
index 372e97d8c..2d088f3df 100755
--- a/scripts/integration-tests.sh
+++ b/scripts/integration-tests.sh
@@ -405,11 +405,6 @@ fi
echo "=== Running Integration Tests ==="
EXCLUDE_TESTS="builtin_tool or safety_with_image or code_interpreter or test_rag"
-# Additional exclusions for vllm setup
-if [[ "$TEST_SETUP" == "vllm" ]]; then
- EXCLUDE_TESTS="${EXCLUDE_TESTS} or test_inference_store_tool_calls"
-fi
-
PYTEST_PATTERN="not( $EXCLUDE_TESTS )"
if [[ -n "$TEST_PATTERN" ]]; then
PYTEST_PATTERN="${PYTEST_PATTERN} and $TEST_PATTERN"
diff --git a/tests/integration/ci_matrix.json b/tests/integration/ci_matrix.json
index 314070eab..858176dff 100644
--- a/tests/integration/ci_matrix.json
+++ b/tests/integration/ci_matrix.json
@@ -2,7 +2,8 @@
"default": [
{"suite": "base", "setup": "ollama"},
{"suite": "vision", "setup": "ollama-vision"},
- {"suite": "responses", "setup": "gpt"}
+ {"suite": "responses", "setup": "gpt"},
+ {"suite": "base-vllm-subset", "setup": "vllm"}
],
"schedules": {
"1 0 * * 0": [
diff --git a/tests/integration/common/recordings/models-64a2277c90f0f42576f60c1030e3a020403d34a95f56931b792d5939f4cebc57-fb68f5a6.json b/tests/integration/common/recordings/models-64a2277c90f0f42576f60c1030e3a020403d34a95f56931b792d5939f4cebc57-fb68f5a6.json
new file mode 100644
index 000000000..00e0862e8
--- /dev/null
+++ b/tests/integration/common/recordings/models-64a2277c90f0f42576f60c1030e3a020403d34a95f56931b792d5939f4cebc57-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": null,
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374291,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-f70298e4ea3e4b4eb7f2cc2deb7a2b01",
+ "object": "model_permission",
+ "created": 1762374291,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/0248ff8a1be5ff5ba88046947059ffbde15a1c52adbeea456bb42abdfc931bd1.json b/tests/integration/inference/recordings/0248ff8a1be5ff5ba88046947059ffbde15a1c52adbeea456bb42abdfc931bd1.json
new file mode 100644
index 000000000..605baf12e
--- /dev/null
+++ b/tests/integration/inference/recordings/0248ff8a1be5ff5ba88046947059ffbde15a1c52adbeea456bb42abdfc931bd1.json
@@ -0,0 +1,3010 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_with_tools_and_streaming[txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:tool_calling]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "system",
+ "content": "Pretend you are a weather assistant."
+ },
+ {
+ "role": "user",
+ "content": "What's the weather like in San Francisco, CA?"
+ }
+ ],
+ "max_tokens": 4096,
+ "stream": true,
+ "tool_choice": "auto",
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "get_weather",
+ "description": "Get the current weather",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "location": {
+ "type": "string",
+ "description": "The city and state (both required), e.g. San Francisco, CA."
+ }
+ },
+ "required": [
+ "location"
+ ]
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": "assistant",
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "\n",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "Okay",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " user",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " is",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " asking",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " about",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " weather",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " in",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " San",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " Francisco",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " CA",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " I",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " need",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " to",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " use",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " get",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "_weather",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " function",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " here",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " The",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " function",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " requires",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " location",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " parameter",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " which",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " in",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " this",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " case",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " is",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " \"",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "San",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " Francisco",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " CA",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "\".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " I",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " should",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " make",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " sure",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " to",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " include",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " both",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " city",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " and",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " state",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " as",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " specified",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " Let",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " me",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " check",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " if",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " there",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "'s",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " any",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " other",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " information",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " needed",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " but",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " user",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " just",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " wants",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " current",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " weather",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " So",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " tool",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " call",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " should",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " be",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " straightforward",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " I",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "'ll",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " format",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " JSON",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " correctly",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " within",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " tool",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "_call",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": " tags",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": ".\n",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "\n\n",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": "chatcmpl-tool-33d90102b2fe4386808056bc3fa9ad17",
+ "function": {
+ "arguments": null,
+ "name": "get_weather"
+ },
+ "type": "function"
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": "{\"location\": \"",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": "San",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": " Francisco",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": ",",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": " CA",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": "\"}",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-0248ff8a1be5",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ }
+ ],
+ "is_streaming": true
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/452805c3c85951c86e4e5dfeef078a2e184866dafee83186cd84932daae1af42.json b/tests/integration/inference/recordings/452805c3c85951c86e4e5dfeef078a2e184866dafee83186cd84932daae1af42.json
new file mode 100644
index 000000000..bbb81ab62
--- /dev/null
+++ b/tests/integration/inference/recordings/452805c3c85951c86e4e5dfeef078a2e184866dafee83186cd84932daae1af42.json
@@ -0,0 +1,84 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestEdgeCases::test_tool_without_schema[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "Call the no args tool"
+ }
+ ],
+ "max_tokens": 4096,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "no_args_tool",
+ "description": "Tool with no arguments",
+ "parameters": {
+ "type": "object",
+ "properties": {}
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-452805c3c859",
+ "choices": [
+ {
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user wants me to call the no args tool. Let me check the available functions. There's only one tool provided, which is the no_args_tool with no arguments. Since the user didn't specify any parameters, I should just return the tool call as instructed. I need to make sure the JSON is correctly formatted and within the XML tags. Alright, that's all I need.\n\n\n",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [
+ {
+ "id": "chatcmpl-tool-7a67269afe214c85924c5171612bbdbd",
+ "function": {
+ "arguments": "{}",
+ "name": "no_args_tool"
+ },
+ "type": "function"
+ }
+ ],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 101,
+ "prompt_tokens": 136,
+ "total_tokens": 237,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/496035259763c1bddb1a3148c2586663d08a5bc31f697d1fc5d9bed1c71f5950.json b/tests/integration/inference/recordings/496035259763c1bddb1a3148c2586663d08a5bc31f697d1fc5d9bed1c71f5950.json
new file mode 100644
index 000000000..04c59b0b7
--- /dev/null
+++ b/tests/integration/inference/recordings/496035259763c1bddb1a3148c2586663d08a5bc31f697d1fc5d9bed1c71f5950.json
@@ -0,0 +1,92 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestOpenAICompatibility::test_openai_chat_completion_with_tools[openai_client-txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "What's the weather in Tokyo?"
+ }
+ ],
+ "max_tokens": 4096,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "get_weather",
+ "description": "Get weather information",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "location": {
+ "type": "string",
+ "description": "City name"
+ }
+ },
+ "required": [
+ "location"
+ ]
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-496035259763",
+ "choices": [
+ {
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user is asking about the weather in Tokyo. I need to use the get_weather function for that. The function requires the location parameter, which in this case is Tokyo. I should make sure to specify \"Tokyo\" as the location. Let me check if there are any other parameters needed, but no, the function only needs the location. So the tool call should be straightforward. I'll format the JSON correctly inside the tool_call tags.\n\n\n",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [
+ {
+ "id": "chatcmpl-tool-959b557fa67e4134a2391f5d35e5d5ae",
+ "function": {
+ "arguments": "{\"location\": \"Tokyo\"}",
+ "name": "get_weather"
+ },
+ "type": "function"
+ }
+ ],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 117,
+ "prompt_tokens": 158,
+ "total_tokens": 275,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/524ead18daaddb6228284820adaa3fb312d2a525cc35e20c181190ddf40793e6.json b/tests/integration/inference/recordings/524ead18daaddb6228284820adaa3fb312d2a525cc35e20c181190ddf40793e6.json
new file mode 100644
index 000000000..b33363e45
--- /dev/null
+++ b/tests/integration/inference/recordings/524ead18daaddb6228284820adaa3fb312d2a525cc35e20c181190ddf40793e6.json
@@ -0,0 +1,92 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestOpenAICompatibility::test_openai_format_preserves_complex_schemas[openai_client-txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "Process this data"
+ }
+ ],
+ "max_tokens": 4096,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "process_data",
+ "description": "Process structured data",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "data": {
+ "$ref": "#/$defs/DataObject"
+ }
+ },
+ "$defs": {
+ "DataObject": {
+ "type": "object",
+ "properties": {
+ "values": {
+ "type": "array",
+ "items": {
+ "type": "number"
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-524ead18daad",
+ "choices": [
+ {
+ "finish_reason": "stop",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user wants me to process the data. Let me check the available tools. There's a function called process_data that takes an object with a 'data' parameter. The data is an array of numbers. But the user hasn't provided any specific data yet. They just said \"Process this data.\" Hmm, maybe they expect me to prompt them for the data first. Wait, maybe there's a misunderstanding. Did they include the data in the conversation history? Let me look back. The user's message is \"Process this data.\" No data provided. Oh, maybe they made a mistake and forgot to include it. I need to ask them to provide the data so I can proceed. Let me confirm if there's any data mentioned. No, the current input is just the instruction. So I should ask the user to supply the data array of numbers to process.\n\n\nPlease provide the structured data you'd like me to process. For example, an array of numbers like `[1, 2, 3]`.",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 212,
+ "prompt_tokens": 180,
+ "total_tokens": 392,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/65eba1be095a7037c4f197f4168b310ebc8afc00aba3946ba498abe2fdbe6a63.json b/tests/integration/inference/recordings/65eba1be095a7037c4f197f4168b310ebc8afc00aba3946ba498abe2fdbe6a63.json
new file mode 100644
index 000000000..a20b23fa2
--- /dev/null
+++ b/tests/integration/inference/recordings/65eba1be095a7037c4f197f4168b310ebc8afc00aba3946ba498abe2fdbe6a63.json
@@ -0,0 +1,2113 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestStreamingWithTools::test_streaming_tool_calls[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "What time is it in UTC?"
+ }
+ ],
+ "max_tokens": 4096,
+ "stream": true,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "get_time",
+ "description": "Get current time",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "timezone": {
+ "type": "string"
+ }
+ }
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": "assistant",
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "\n",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "Okay",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " user",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " is",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " asking",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " for",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " current",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " time",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " in",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " UTC",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " Let",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " me",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " check",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " tools",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " available",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " There",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "'s",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " a",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " function",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " called",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " get",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "_time",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " that",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " takes",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " a",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " timezone",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " parameter",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " Since",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " UTC",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " is",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " standard",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " time",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " zone",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ",",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " I",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " need",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " to",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " specify",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " that",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " So",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " I",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "'ll",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " call",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " get",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "_time",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " with",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " timezone",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " set",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " to",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " \"",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "UTC",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "\".",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " That",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " should",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " retrieve",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " the",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " time",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": " correctly",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": ".\n",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "\n\n",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": "chatcmpl-tool-41faa6bedd074d51a6335cd2447deeab",
+ "function": {
+ "arguments": null,
+ "name": "get_time"
+ },
+ "type": "function"
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": "{\"timezone\": \"",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": "UTC",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": null,
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": [
+ {
+ "index": 0,
+ "id": null,
+ "function": {
+ "arguments": "\"}",
+ "name": null
+ },
+ "type": null
+ }
+ ]
+ },
+ "finish_reason": null,
+ "index": 0,
+ "logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ },
+ {
+ "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+ "__data__": {
+ "id": "rec-65eba1be095a",
+ "choices": [
+ {
+ "delta": {
+ "content": "",
+ "function_call": null,
+ "refusal": null,
+ "role": null,
+ "tool_calls": null
+ },
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion.chunk",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": null
+ }
+ }
+ ],
+ "is_streaming": true
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/744052775cf90e30dac587e6b809d41a8cc37adc29c500eecee2727f428cbf5a.json b/tests/integration/inference/recordings/744052775cf90e30dac587e6b809d41a8cc37adc29c500eecee2727f428cbf5a.json
new file mode 100644
index 000000000..539668be7
--- /dev/null
+++ b/tests/integration/inference/recordings/744052775cf90e30dac587e6b809d41a8cc37adc29c500eecee2727f428cbf5a.json
@@ -0,0 +1,98 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_with_tools[txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:tool_calling]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "system",
+ "content": "Pretend you are a weather assistant."
+ },
+ {
+ "role": "user",
+ "content": "What's the weather like in San Francisco, CA?"
+ }
+ ],
+ "max_tokens": 4096,
+ "stream": false,
+ "tool_choice": "auto",
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "get_weather",
+ "description": "Get the current weather",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "location": {
+ "type": "string",
+ "description": "The city and state (both required), e.g. San Francisco, CA."
+ }
+ },
+ "required": [
+ "location"
+ ]
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-744052775cf9",
+ "choices": [
+ {
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user is asking about the weather in San Francisco, CA. I need to use the get_weather function. The function requires the location parameter, which is provided as San Francisco, CA. I should make sure to format the arguments correctly as a JSON object. Let me check the required parameters again. The location is required, so I can't omit it. I'll structure the tool call with the name \"get_weather\" and the arguments including \"location\": \"San Francisco, CA\". That should get the current weather information for the user.\n\n\n",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [
+ {
+ "id": "chatcmpl-tool-b59dc311dd914d3dbd6d455b122bc39c",
+ "function": {
+ "arguments": "{\"location\": \"San Francisco, CA\"}",
+ "name": "get_weather"
+ },
+ "type": "function"
+ }
+ ],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 138,
+ "prompt_tokens": 185,
+ "total_tokens": 323,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/77cf218283607bfac37623e1bb4e6f33cae670df7d6995d432bca34c5dfb0e43.json b/tests/integration/inference/recordings/77cf218283607bfac37623e1bb4e6f33cae670df7d6995d432bca34c5dfb0e43.json
new file mode 100644
index 000000000..05b4e2609
--- /dev/null
+++ b/tests/integration/inference/recordings/77cf218283607bfac37623e1bb4e6f33cae670df7d6995d432bca34c5dfb0e43.json
@@ -0,0 +1,67 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_with_tool_choice_none[txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:tool_calling]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "system",
+ "content": "Pretend you are a weather assistant."
+ },
+ {
+ "role": "user",
+ "content": "What's the weather like in San Francisco, CA?"
+ }
+ ],
+ "max_tokens": 4096,
+ "stream": false
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-77cf21828360",
+ "choices": [
+ {
+ "finish_reason": "stop",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user is asking about the weather in San Francisco, CA. I need to check the current weather conditions. But wait, I can't access real-time data. I should mention that I can't provide the current weather forecast and ask them to check a reliable source like the National Weather Service or a weather app. Also, maybe suggest they can provide more details if they need help with something else related to the weather.\n\n\nI'm sorry, but I can't provide real-time weather information. However, you can check the current weather for San Francisco, CA using the National Weather Service (NWS) website, weather apps like Weather.com, or local meteorological services. Let me know if there's anything else I can assist with!",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 154,
+ "prompt_tokens": 33,
+ "total_tokens": 187,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/853f6a700b98d71d390b7d366e27133a22772fbdf11863158349c1b0625bbc72.json b/tests/integration/inference/recordings/853f6a700b98d71d390b7d366e27133a22772fbdf11863158349c1b0625bbc72.json
new file mode 100644
index 000000000..2f6e4d3fc
--- /dev/null
+++ b/tests/integration/inference/recordings/853f6a700b98d71d390b7d366e27133a22772fbdf11863158349c1b0625bbc72.json
@@ -0,0 +1,128 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestEdgeCases::test_multiple_tools_with_different_schemas[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "Use one of the available tools"
+ }
+ ],
+ "max_tokens": 4096,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "simple",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "x": {
+ "type": "string"
+ }
+ }
+ }
+ }
+ },
+ {
+ "type": "function",
+ "function": {
+ "name": "complex",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "data": {
+ "$ref": "#/$defs/Complex"
+ }
+ },
+ "$defs": {
+ "Complex": {
+ "type": "object",
+ "properties": {
+ "nested": {
+ "type": "array",
+ "items": {
+ "type": "number"
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ },
+ {
+ "type": "function",
+ "function": {
+ "name": "with_output",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "input": {
+ "type": "string"
+ }
+ }
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-853f6a700b98",
+ "choices": [
+ {
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, let's see. The user wants me to use one of the available tools. The tools provided are simple, complex, and with_output. The simple function takes an argument 'x' of type string. The complex function requires a 'data' parameter that's an object with a nested array of numbers. The with_output function takes an input string.\n\nThe user's query is about using a tool, but there's no specific function name mentioned. Wait, maybe the user expects me to choose one based on the context. Since the tools are available, but the query is a general instruction, perhaps I should ask for clarification. However, the instructions say to use one of the tools if possible. Since the user hasn't specified a particular function, maybe I should check if there's any implicit function needed. But looking at the tools, none are directly related to the query. The user might need to specify which tool to use. Alternatively, maybe the answer is to call the simple function with an example input. But without more context, it's hard to tell. Wait, maybe the user expects me to choose the simplest one. Let's go with the simple function first. So the tool call would be to the simple function with x set to some value. But the user hasn't provided a specific value. Maybe I should state that the tool requires a value. But according to the instructions, if possible, use one of the tools. Since the user hasn't given a value, perhaps the answer is to call the simple function with an example. But the parameters for the simple function require 'x' which is a string. Maybe the user expects me to proceed without needing more info. So I'll proceed by calling the simple function with x as \"example\".\n\n\n",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [
+ {
+ "id": "chatcmpl-tool-12e2ba0189cf484bb936cbb254a5c32a",
+ "function": {
+ "arguments": "{\"x\": \"example\"}",
+ "name": "simple"
+ },
+ "type": "function"
+ }
+ ],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 378,
+ "prompt_tokens": 265,
+ "total_tokens": 643,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/cfb292c0f41dbc4a2c0fb39016760f6c23c248a7bbffea19ac6bcab7bf25292d.json b/tests/integration/inference/recordings/cfb292c0f41dbc4a2c0fb39016760f6c23c248a7bbffea19ac6bcab7bf25292d.json
new file mode 100644
index 000000000..fdec100bb
--- /dev/null
+++ b/tests/integration/inference/recordings/cfb292c0f41dbc4a2c0fb39016760f6c23c248a7bbffea19ac6bcab7bf25292d.json
@@ -0,0 +1,114 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestChatCompletionWithTools::test_tool_with_complex_schema[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "Book a flight from SFO to JFK for John Doe"
+ }
+ ],
+ "max_tokens": 4096,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "book_flight",
+ "description": "Book a flight",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "flight": {
+ "$ref": "#/$defs/FlightInfo"
+ },
+ "passenger": {
+ "$ref": "#/$defs/Passenger"
+ }
+ },
+ "required": [
+ "flight",
+ "passenger"
+ ],
+ "$defs": {
+ "FlightInfo": {
+ "type": "object",
+ "properties": {
+ "from": {
+ "type": "string"
+ },
+ "to": {
+ "type": "string"
+ },
+ "date": {
+ "type": "string",
+ "format": "date"
+ }
+ }
+ },
+ "Passenger": {
+ "type": "object",
+ "properties": {
+ "name": {
+ "type": "string"
+ },
+ "age": {
+ "type": "integer"
+ }
+ }
+ }
+ }
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-cfb292c0f41d",
+ "choices": [
+ {
+ "finish_reason": "stop",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user wants to book a flight from SFO to JFK for John Doe. Let me check the tools available. The provided function is book_flight, which requires flight information and a passenger. The parameters needed are flight (as a FlightInfo object) and passenger (with name and age). The user mentioned SFO to JFK, so the flight details are from and to. The passenger's name is John Doe, but the age isn't provided. Wait, the function parameters require the passenger's name and age, but the user only mentioned the name. Maybe the age is missing? But the user didn't specify it, so perhaps I should note that the age is required. However, the function's required parameters are flight and passenger, so even if age is missing, the function can't be called without it. So I need to include both flight info and passenger details. The user's message only gives the name and destination, not the flight details or age. Therefore, I need to ask for the flight details and the passenger's age. But the user hasn't provided those. So I can't proceed with the function call. Wait, but maybe the user expects me to assume some default? No, the function requires all parameters. Since the user hasn't provided flight details or age, I can't call the function. So the correct response is to prompt the user for those details.\n\n\nThe booking requires the flight details and passenger's age. Could you provide the flight number and John Doe's age?",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 310,
+ "prompt_tokens": 261,
+ "total_tokens": 571,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/df353403c7fb59ed88c52269261b3dd9b75f681f8bb5431b4f07006d6c08aa7c.json b/tests/integration/inference/recordings/df353403c7fb59ed88c52269261b3dd9b75f681f8bb5431b4f07006d6c08aa7c.json
new file mode 100644
index 000000000..eb6eb8eb2
--- /dev/null
+++ b/tests/integration/inference/recordings/df353403c7fb59ed88c52269261b3dd9b75f681f8bb5431b4f07006d6c08aa7c.json
@@ -0,0 +1,96 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_structured_output[txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:structured_output]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "system",
+ "content": "You are a helpful assistant. Michael Jordan was born in 1963. His first name is \"Michael\", He played basketball for the Chicago Bulls for 15 seasons and was drafted in 1984"
+ },
+ {
+ "role": "user",
+ "content": "Please give me information about Michael Jordan."
+ }
+ ],
+ "max_tokens": 4096,
+ "response_format": {
+ "type": "json_schema",
+ "json_schema": {
+ "name": "AnswerFormat",
+ "schema": {
+ "properties": {
+ "first_name": {
+ "title": "First Name",
+ "type": "string"
+ },
+ "last_name": {
+ "title": "Last Name",
+ "type": "string"
+ },
+ "year_of_birth": {
+ "title": "Year Of Birth",
+ "type": "integer"
+ }
+ },
+ "required": [
+ "first_name",
+ "last_name",
+ "year_of_birth"
+ ],
+ "title": "AnswerFormat",
+ "type": "object"
+ }
+ }
+ },
+ "stream": false
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-df353403c7fb",
+ "choices": [
+ {
+ "finish_reason": "stop",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "{\"first_name\": \"Michael\", \"last_name\": \"Jordan\", \"year_of_birth\": 1963}",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 28,
+ "prompt_tokens": 66,
+ "total_tokens": 94,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/e89112e7735fccc5ad9ebe6a96454953aed0ba2501cabfaa80b742c2bf371cbc.json b/tests/integration/inference/recordings/e89112e7735fccc5ad9ebe6a96454953aed0ba2501cabfaa80b742c2bf371cbc.json
new file mode 100644
index 000000000..856684a55
--- /dev/null
+++ b/tests/integration/inference/recordings/e89112e7735fccc5ad9ebe6a96454953aed0ba2501cabfaa80b742c2bf371cbc.json
@@ -0,0 +1,92 @@
+{
+ "test_id": "tests/integration/inference/test_tools_with_schemas.py::TestChatCompletionWithTools::test_simple_tool_call[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/chat/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "messages": [
+ {
+ "role": "user",
+ "content": "What's the weather in San Francisco?"
+ }
+ ],
+ "max_tokens": 4096,
+ "tools": [
+ {
+ "type": "function",
+ "function": {
+ "name": "get_weather",
+ "description": "Get weather for a location",
+ "parameters": {
+ "type": "object",
+ "properties": {
+ "location": {
+ "type": "string",
+ "description": "City name"
+ }
+ },
+ "required": [
+ "location"
+ ]
+ }
+ }
+ }
+ ]
+ },
+ "endpoint": "/v1/chat/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+ "__data__": {
+ "id": "rec-e89112e7735f",
+ "choices": [
+ {
+ "finish_reason": "tool_calls",
+ "index": 0,
+ "logprobs": null,
+ "message": {
+ "content": "\nOkay, the user is asking for the weather in San Francisco. I need to check if there's a function available for that. Looking at the tools provided, there's a function called get_weather that requires a location parameter. The description says it gets weather for a location, and the parameter is the city name. The user provided \"San Francisco\" as the location, so I should call the get_weather function with \"San Francisco\" as the argument. I don't see any other parameters needed here, so the tool call should be straightforward. Just make sure the city name is correctly formatted in JSON.\n\n\n",
+ "refusal": null,
+ "role": "assistant",
+ "annotations": null,
+ "audio": null,
+ "function_call": null,
+ "tool_calls": [
+ {
+ "id": "chatcmpl-tool-feead29842dc40b2831c41ed397f555f",
+ "function": {
+ "arguments": "{\"location\": \"San Francisco\"}",
+ "name": "get_weather"
+ },
+ "type": "function"
+ }
+ ],
+ "reasoning_content": null
+ },
+ "stop_reason": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "chat.completion",
+ "service_tier": null,
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 146,
+ "prompt_tokens": 161,
+ "total_tokens": 307,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "prompt_logprobs": null,
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/f02f1bfd75adaea87b91dedc59430b99015b5ed0e2bbf24418a31146ffcbca9b.json b/tests/integration/inference/recordings/f02f1bfd75adaea87b91dedc59430b99015b5ed0e2bbf24418a31146ffcbca9b.json
new file mode 100644
index 000000000..28f7d8296
--- /dev/null
+++ b/tests/integration/inference/recordings/f02f1bfd75adaea87b91dedc59430b99015b5ed0e2bbf24418a31146ffcbca9b.json
@@ -0,0 +1,53 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/completions",
+ "headers": {},
+ "body": {
+ "model": "Qwen/Qwen3-0.6B",
+ "prompt": "I am feeling really sad today.",
+ "stream": false,
+ "extra_body": {
+ "guided_choice": [
+ "joy",
+ "sadness"
+ ]
+ }
+ },
+ "endpoint": "/v1/completions",
+ "model": "Qwen/Qwen3-0.6B"
+ },
+ "response": {
+ "body": {
+ "__type__": "openai.types.completion.Completion",
+ "__data__": {
+ "id": "rec-f02f1bfd75ad",
+ "choices": [
+ {
+ "finish_reason": "stop",
+ "index": 0,
+ "logprobs": null,
+ "text": "joy",
+ "stop_reason": null,
+ "prompt_logprobs": null
+ }
+ ],
+ "created": 0,
+ "model": "Qwen/Qwen3-0.6B",
+ "object": "text_completion",
+ "system_fingerprint": null,
+ "usage": {
+ "completion_tokens": 2,
+ "prompt_tokens": 7,
+ "total_tokens": 9,
+ "completion_tokens_details": null,
+ "prompt_tokens_details": null
+ },
+ "kv_transfer_params": null
+ }
+ },
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-0037f2d2065a360cfcc36c35f138318cfc6508e743ff9423da4b7b1d7bfd4f3f-fb68f5a6.json b/tests/integration/inference/recordings/models-0037f2d2065a360cfcc36c35f138318cfc6508e743ff9423da4b7b1d7bfd4f3f-fb68f5a6.json
new file mode 100644
index 000000000..7256ae75d
--- /dev/null
+++ b/tests/integration/inference/recordings/models-0037f2d2065a360cfcc36c35f138318cfc6508e743ff9423da4b7b1d7bfd4f3f-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375180,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-aeeb49e5e51c42fa94562780165bd620",
+ "object": "model_permission",
+ "created": 1762375180,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-009fb75503cf565d6c97f70deb8235432b0020b93d55e3b33ea093664c4bbc82-fb68f5a6.json b/tests/integration/inference/recordings/models-009fb75503cf565d6c97f70deb8235432b0020b93d55e3b33ea093664c4bbc82-fb68f5a6.json
new file mode 100644
index 000000000..e0f5fa68f
--- /dev/null
+++ b/tests/integration/inference/recordings/models-009fb75503cf565d6c97f70deb8235432b0020b93d55e3b33ea093664c4bbc82-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375115,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-feec0a894be04f738e12b596ff163b64",
+ "object": "model_permission",
+ "created": 1762375115,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-01e6ee9852f532d9b0d82dde2e7c831d698e81dea1be69433050d42643f35edc-fb68f5a6.json b/tests/integration/inference/recordings/models-01e6ee9852f532d9b0d82dde2e7c831d698e81dea1be69433050d42643f35edc-fb68f5a6.json
new file mode 100644
index 000000000..0eb0a26a6
--- /dev/null
+++ b/tests/integration/inference/recordings/models-01e6ee9852f532d9b0d82dde2e7c831d698e81dea1be69433050d42643f35edc-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_stop_sequence[txt=vllm/Qwen/Qwen3-0.6B-inference:completion:stop_sequence]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374330,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-119e17052e4c4c13bd791af3138d5360",
+ "object": "model_permission",
+ "created": 1762374330,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-10370bf5307b2fc971b8e53bdcc4e9eb4d3d76fe8ecdb31231b59576a612e972-fb68f5a6.json b/tests/integration/inference/recordings/models-10370bf5307b2fc971b8e53bdcc4e9eb4d3d76fe8ecdb31231b59576a612e972-fb68f5a6.json
new file mode 100644
index 000000000..dc7c97f4f
--- /dev/null
+++ b/tests/integration/inference/recordings/models-10370bf5307b2fc971b8e53bdcc4e9eb4d3d76fe8ecdb31231b59576a612e972-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375226,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-c6ae673fda084519b3c67947896cd3b0",
+ "object": "model_permission",
+ "created": 1762375226,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-1312e0d8579e9b0e6dcb222272de34115277db71c6c560872fa13722197f881f-fb68f5a6.json b/tests/integration/inference/recordings/models-1312e0d8579e9b0e6dcb222272de34115277db71c6c560872fa13722197f881f-fb68f5a6.json
new file mode 100644
index 000000000..833003741
--- /dev/null
+++ b/tests/integration/inference/recordings/models-1312e0d8579e9b0e6dcb222272de34115277db71c6c560872fa13722197f881f-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374573,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-3f422354a81e491b87f93d5b192a0e1a",
+ "object": "model_permission",
+ "created": 1762374573,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-134e731d073e9e07eb9782bbe292167f8ad08157a15150ce92135854d04050fc-fb68f5a6.json b/tests/integration/inference/recordings/models-134e731d073e9e07eb9782bbe292167f8ad08157a15150ce92135854d04050fc-fb68f5a6.json
new file mode 100644
index 000000000..df660a0f1
--- /dev/null
+++ b/tests/integration/inference/recordings/models-134e731d073e9e07eb9782bbe292167f8ad08157a15150ce92135854d04050fc-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_01]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374305,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-794e16e59ddb4216a8bedfdf485b8f24",
+ "object": "model_permission",
+ "created": 1762374305,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-14c0905df1b177d2f85b30b0285b0ffdc88d1a7b290e2155fb7a01f3c1436ca0-fb68f5a6.json b/tests/integration/inference/recordings/models-14c0905df1b177d2f85b30b0285b0ffdc88d1a7b290e2155fb7a01f3c1436ca0-fb68f5a6.json
new file mode 100644
index 000000000..fed71ffa7
--- /dev/null
+++ b/tests/integration/inference/recordings/models-14c0905df1b177d2f85b30b0285b0ffdc88d1a7b290e2155fb7a01f3c1436ca0-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=vllm/Qwen/Qwen3-0.6B-True]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374317,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-ff7d26d076eb4373a0631a80fe3ae063",
+ "object": "model_permission",
+ "created": 1762374317,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-1bc879637162ba23badeea66c4c25a638869a3e90d16ef3e84dea1a613e7192e-fb68f5a6.json b/tests/integration/inference/recordings/models-1bc879637162ba23badeea66c4c25a638869a3e90d16ef3e84dea1a613e7192e-fb68f5a6.json
new file mode 100644
index 000000000..9a532d386
--- /dev/null
+++ b/tests/integration/inference/recordings/models-1bc879637162ba23badeea66c4c25a638869a3e90d16ef3e84dea1a613e7192e-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_02]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375033,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-2a16fede981b43be9e1cbe3dbedd1e74",
+ "object": "model_permission",
+ "created": 1762375033,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-2b9bac5da1a03c0b572bc019cc0c50904d49e6193990ca245908f4535bcaab43-fb68f5a6.json b/tests/integration/inference/recordings/models-2b9bac5da1a03c0b572bc019cc0c50904d49e6193990ca245908f4535bcaab43-fb68f5a6.json
new file mode 100644
index 000000000..ab3269b57
--- /dev/null
+++ b/tests/integration/inference/recordings/models-2b9bac5da1a03c0b572bc019cc0c50904d49e6193990ca245908f4535bcaab43-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374297,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-4bc93704559a4e1d8492aeec7222040c",
+ "object": "model_permission",
+ "created": 1762374297,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-394c30370fe5b724c5fe1292984373b281d47b2ac0d49e8b598f13cf100b3ad8-fb68f5a6.json b/tests/integration/inference/recordings/models-394c30370fe5b724c5fe1292984373b281d47b2ac0d49e8b598f13cf100b3ad8-fb68f5a6.json
new file mode 100644
index 000000000..8237cc20c
--- /dev/null
+++ b/tests/integration/inference/recordings/models-394c30370fe5b724c5fe1292984373b281d47b2ac0d49e8b598f13cf100b3ad8-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374532,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-e353aa079d5145c19953791ac99daeba",
+ "object": "model_permission",
+ "created": 1762374532,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-3f4208962fdb2be3e7057777fc93a149890bd1dfa8a92597e176f23658e86cd8-fb68f5a6.json b/tests/integration/inference/recordings/models-3f4208962fdb2be3e7057777fc93a149890bd1dfa8a92597e176f23658e86cd8-fb68f5a6.json
new file mode 100644
index 000000000..14b37fb0a
--- /dev/null
+++ b/tests/integration/inference/recordings/models-3f4208962fdb2be3e7057777fc93a149890bd1dfa8a92597e176f23658e86cd8-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-True]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375260,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-10c27d1c9e324b18b65321b422e19af9",
+ "object": "model_permission",
+ "created": 1762375260,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-4a729b00af209ad60846d1904e5973ad081aa5f595de50f5ef1aae304cb67ef3-fb68f5a6.json b/tests/integration/inference/recordings/models-4a729b00af209ad60846d1904e5973ad081aa5f595de50f5ef1aae304cb67ef3-fb68f5a6.json
new file mode 100644
index 000000000..4af25e17a
--- /dev/null
+++ b/tests/integration/inference/recordings/models-4a729b00af209ad60846d1904e5973ad081aa5f595de50f5ef1aae304cb67ef3-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[openai_client-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_02]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375040,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-f01c211577294936958dd28046c89dba",
+ "object": "model_permission",
+ "created": 1762375040,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-4f62bcb9cdf74f4c2ed804038def162f18ad384182b0f174918607e9ed3c1515-fb68f5a6.json b/tests/integration/inference/recordings/models-4f62bcb9cdf74f4c2ed804038def162f18ad384182b0f174918607e9ed3c1515-fb68f5a6.json
new file mode 100644
index 000000000..54b48967b
--- /dev/null
+++ b/tests/integration/inference/recordings/models-4f62bcb9cdf74f4c2ed804038def162f18ad384182b0f174918607e9ed3c1515-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:non_streaming_02]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375266,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-7166a6fcd331435eb2d0f0a6b23382ed",
+ "object": "model_permission",
+ "created": 1762375266,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-54b420cdb98a0149a618088f55746e26b7bf6e7c5ebf5fa07c13ec9e366521d3-fb68f5a6.json b/tests/integration/inference/recordings/models-54b420cdb98a0149a618088f55746e26b7bf6e7c5ebf5fa07c13ec9e366521d3-fb68f5a6.json
new file mode 100644
index 000000000..30a33793b
--- /dev/null
+++ b/tests/integration/inference/recordings/models-54b420cdb98a0149a618088f55746e26b7bf6e7c5ebf5fa07c13ec9e366521d3-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[openai_client-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_01]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374301,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-cd16b092c5a04e719ddf786f0c3e935e",
+ "object": "model_permission",
+ "created": 1762374301,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-613f5d11a8cda7126115f96650334fde0a0457a6b4a2605bc15eec9b50a6956c-fb68f5a6.json b/tests/integration/inference/recordings/models-613f5d11a8cda7126115f96650334fde0a0457a6b4a2605bc15eec9b50a6956c-fb68f5a6.json
new file mode 100644
index 000000000..4193dce51
--- /dev/null
+++ b/tests/integration/inference/recordings/models-613f5d11a8cda7126115f96650334fde0a0457a6b4a2605bc15eec9b50a6956c-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming[txt=vllm/Qwen/Qwen3-0.6B-inference:completion:sanity]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374295,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-9f71adbb206846bb9d0e12834e41551e",
+ "object": "model_permission",
+ "created": 1762374295,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-62a361f55d61a98ea0863e9acfb5ab5d540c5d19e791415ee476474f7f1ed90f-fb68f5a6.json b/tests/integration/inference/recordings/models-62a361f55d61a98ea0863e9acfb5ab5d540c5d19e791415ee476474f7f1ed90f-fb68f5a6.json
new file mode 100644
index 000000000..d5916fff7
--- /dev/null
+++ b/tests/integration/inference/recordings/models-62a361f55d61a98ea0863e9acfb5ab5d540c5d19e791415ee476474f7f1ed90f-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_logprobs_streaming[txt=vllm/Qwen/Qwen3-0.6B-inference:completion:log_probs]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374342,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-a8b7b38c40584a03b4b346b6c181fb93",
+ "object": "model_permission",
+ "created": 1762374342,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-668fc72f70ac72d5c112fe79d86d5c790611456b3f0102832f27e6edd420ab54-fb68f5a6.json b/tests/integration/inference/recordings/models-668fc72f70ac72d5c112fe79d86d5c790611456b3f0102832f27e6edd420ab54-fb68f5a6.json
new file mode 100644
index 000000000..1542aa0cf
--- /dev/null
+++ b/tests/integration/inference/recordings/models-668fc72f70ac72d5c112fe79d86d5c790611456b3f0102832f27e6edd420ab54-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:non_streaming_01]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375235,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-dd48560646f141298f5cc2ef3467e54b",
+ "object": "model_permission",
+ "created": 1762375235,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-702eee4572e9b17ff0b0fdd55b10021f7077f0afcba922d6a53db0b537542518-fb68f5a6.json b/tests/integration/inference/recordings/models-702eee4572e9b17ff0b0fdd55b10021f7077f0afcba922d6a53db0b537542518-fb68f5a6.json
new file mode 100644
index 000000000..fed0e7785
--- /dev/null
+++ b/tests/integration/inference/recordings/models-702eee4572e9b17ff0b0fdd55b10021f7077f0afcba922d6a53db0b537542518-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374500,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-0ba0c3a54dcb4e57bc0308fd54425933",
+ "object": "model_permission",
+ "created": 1762374500,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-723d37a5bceab199cff076a0dcc2d4ee7596b7c800f13c64f6a6ecdbf4ed2f3a-fb68f5a6.json b/tests/integration/inference/recordings/models-723d37a5bceab199cff076a0dcc2d4ee7596b7c800f13c64f6a6ecdbf4ed2f3a-fb68f5a6.json
new file mode 100644
index 000000000..f53aadba5
--- /dev/null
+++ b/tests/integration/inference/recordings/models-723d37a5bceab199cff076a0dcc2d4ee7596b7c800f13c64f6a6ecdbf4ed2f3a-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=vllm/Qwen/Qwen3-0.6B-True]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374311,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-e95a9ed7439245b5995add97fb50f765",
+ "object": "model_permission",
+ "created": 1762374311,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-768c497339830cf86ddd7843f33d0ed06b3bce3ef2ae9f854364b534ba8cafb7-fb68f5a6.json b/tests/integration/inference/recordings/models-768c497339830cf86ddd7843f33d0ed06b3bce3ef2ae9f854364b534ba8cafb7-fb68f5a6.json
new file mode 100644
index 000000000..5f5d13e94
--- /dev/null
+++ b/tests/integration/inference/recordings/models-768c497339830cf86ddd7843f33d0ed06b3bce3ef2ae9f854364b534ba8cafb7-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375099,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-6b5eba46536f43df902871dd257e1676",
+ "object": "model_permission",
+ "created": 1762375099,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-7b0f2493d699e58cdfe0a9dab38f4423771c8ebced2020b1e15cbb35470c1ca2-fb68f5a6.json b/tests/integration/inference/recordings/models-7b0f2493d699e58cdfe0a9dab38f4423771c8ebced2020b1e15cbb35470c1ca2-fb68f5a6.json
new file mode 100644
index 000000000..69b91db75
--- /dev/null
+++ b/tests/integration/inference/recordings/models-7b0f2493d699e58cdfe0a9dab38f4423771c8ebced2020b1e15cbb35470c1ca2-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_base64[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375207,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-bbfbcf20cac146e0ae5e45ae6a42632d",
+ "object": "model_permission",
+ "created": 1762375207,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-7ed97509ff199eabe1380caa36b9e5934e9d04a9cafcfa2d21d20f6f85679ae4-fb68f5a6.json b/tests/integration/inference/recordings/models-7ed97509ff199eabe1380caa36b9e5934e9d04a9cafcfa2d21d20f6f85679ae4-fb68f5a6.json
new file mode 100644
index 000000000..d6d7b81a0
--- /dev/null
+++ b/tests/integration/inference/recordings/models-7ed97509ff199eabe1380caa36b9e5934e9d04a9cafcfa2d21d20f6f85679ae4-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_02]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375273,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-4935d35e00fd4acdbe78662f42342e77",
+ "object": "model_permission",
+ "created": 1762375273,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-805e6b510b1ab33505a1af85c0d2a766cd3415512212d80f6292ca0ef5c359e1-fb68f5a6.json b/tests/integration/inference/recordings/models-805e6b510b1ab33505a1af85c0d2a766cd3415512212d80f6292ca0ef5c359e1-fb68f5a6.json
new file mode 100644
index 000000000..1e7cb92bf
--- /dev/null
+++ b/tests/integration/inference/recordings/models-805e6b510b1ab33505a1af85c0d2a766cd3415512212d80f6292ca0ef5c359e1-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_base64_batch_processing[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374591,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-e19031997a1e44d99c8b5ae55725a887",
+ "object": "model_permission",
+ "created": 1762374591,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-860b7e8309e0761e20e845be75c0a28d759384a367f6308f2a921702318a5dba-fb68f5a6.json b/tests/integration/inference/recordings/models-860b7e8309e0761e20e845be75c0a28d759384a367f6308f2a921702318a5dba-fb68f5a6.json
new file mode 100644
index 000000000..2e4cb4cb0
--- /dev/null
+++ b/tests/integration/inference/recordings/models-860b7e8309e0761e20e845be75c0a28d759384a367f6308f2a921702318a5dba-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:non_streaming_02]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375027,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-ec44b40a73b04912a837001376b59cff",
+ "object": "model_permission",
+ "created": 1762375027,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-8903569d538f9836ac6251d90c4668d3057e8e0ced847a08fd7a6faedb5710c3-fb68f5a6.json b/tests/integration/inference/recordings/models-8903569d538f9836ac6251d90c4668d3057e8e0ced847a08fd7a6faedb5710c3-fb68f5a6.json
new file mode 100644
index 000000000..4ab79796c
--- /dev/null
+++ b/tests/integration/inference/recordings/models-8903569d538f9836ac6251d90c4668d3057e8e0ced847a08fd7a6faedb5710c3-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374356,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-3203232f1dbd426aba98ef1593dd3c01",
+ "object": "model_permission",
+ "created": 1762374356,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-8aa8c593dd64639678c294146fd56804393856c6e85197e6317ebd88351be21d-fb68f5a6.json b/tests/integration/inference/recordings/models-8aa8c593dd64639678c294146fd56804393856c6e85197e6317ebd88351be21d-fb68f5a6.json
new file mode 100644
index 000000000..f2c124b73
--- /dev/null
+++ b/tests/integration/inference/recordings/models-8aa8c593dd64639678c294146fd56804393856c6e85197e6317ebd88351be21d-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_01]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375248,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-5efe67a621074e979edaaf8fcfee9a80",
+ "object": "model_permission",
+ "created": 1762375248,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-8fc4c7b563b9bd423b74dcb4683039248f41d86c02703bd2dce845d972c9ae6f-fb68f5a6.json b/tests/integration/inference/recordings/models-8fc4c7b563b9bd423b74dcb4683039248f41d86c02703bd2dce845d972c9ae6f-fb68f5a6.json
new file mode 100644
index 000000000..0b5b6e4ed
--- /dev/null
+++ b/tests/integration/inference/recordings/models-8fc4c7b563b9bd423b74dcb4683039248f41d86c02703bd2dce845d972c9ae6f-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_user_parameter[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375135,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-5509cf924e5e4fc89091e4593f264258",
+ "object": "model_permission",
+ "created": 1762375135,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-99ae704b53e3e3150cac5cd579e446e6545a4ab6a63048ce00ee1fbe5fbf1b4e-fb68f5a6.json b/tests/integration/inference/recordings/models-99ae704b53e3e3150cac5cd579e446e6545a4ab6a63048ce00ee1fbe5fbf1b4e-fb68f5a6.json
new file mode 100644
index 000000000..f8ded3ee4
--- /dev/null
+++ b/tests/integration/inference/recordings/models-99ae704b53e3e3150cac5cd579e446e6545a4ab6a63048ce00ee1fbe5fbf1b4e-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[openai_client-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:non_streaming_01]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374301,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-72ed55b56df1471b9f71c48bacf8b768",
+ "object": "model_permission",
+ "created": 1762374301,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-9a36a281899f0800f085473f5f0185b09a02022607b965ac08b4db2e9e7eabc9-fb68f5a6.json b/tests/integration/inference/recordings/models-9a36a281899f0800f085473f5f0185b09a02022607b965ac08b4db2e9e7eabc9-fb68f5a6.json
new file mode 100644
index 000000000..32ecdf0b6
--- /dev/null
+++ b/tests/integration/inference/recordings/models-9a36a281899f0800f085473f5f0185b09a02022607b965ac08b4db2e9e7eabc9-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_non_streaming_suffix[txt=vllm/Qwen/Qwen3-0.6B-inference:completion:suffix]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374295,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-abbbfbb49abc4312b2b2011d4d2ba19b",
+ "object": "model_permission",
+ "created": 1762374295,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-9beac41c66cbe8568bb72b5ba0f5608597ef8a14b42585c22b1e7c45526537c1-fb68f5a6.json b/tests/integration/inference/recordings/models-9beac41c66cbe8568bb72b5ba0f5608597ef8a14b42585c22b1e7c45526537c1-fb68f5a6.json
new file mode 100644
index 000000000..454b7223f
--- /dev/null
+++ b/tests/integration/inference/recordings/models-9beac41c66cbe8568bb72b5ba0f5608597ef8a14b42585c22b1e7c45526537c1-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_single_string[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375065,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-d943fbda14264715906334300853cec7",
+ "object": "model_permission",
+ "created": 1762375065,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-a495ae010d48bb3649c822e3299e819c164c2311db231c81296ff4c72e6f81cb-fb68f5a6.json b/tests/integration/inference/recordings/models-a495ae010d48bb3649c822e3299e819c164c2311db231c81296ff4c72e6f81cb-fb68f5a6.json
new file mode 100644
index 000000000..1eded64dd
--- /dev/null
+++ b/tests/integration/inference/recordings/models-a495ae010d48bb3649c822e3299e819c164c2311db231c81296ff4c72e6f81cb-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming_with_file[txt=vllm/Qwen/Qwen3-0.6B]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374323,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-15a0a1106fff4fdd8ce7574373fe3cee",
+ "object": "model_permission",
+ "created": 1762374323,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-a77b3cb7370fd9f46e6ea12d72e1d9a8e7515f745289e93e5eb4a21d0e7b71b7-fb68f5a6.json b/tests/integration/inference/recordings/models-a77b3cb7370fd9f46e6ea12d72e1d9a8e7515f745289e93e5eb4a21d0e7b71b7-fb68f5a6.json
new file mode 100644
index 000000000..9501f622a
--- /dev/null
+++ b/tests/integration/inference/recordings/models-a77b3cb7370fd9f46e6ea12d72e1d9a8e7515f745289e93e5eb4a21d0e7b71b7-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375082,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-ef1d3bc6fefc432380ef0eabdf216fd3",
+ "object": "model_permission",
+ "created": 1762375082,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-a82e913e058618dcb30b269a54d4e6a9cb1e0017a42efe04480874fe957194d4-fb68f5a6.json b/tests/integration/inference/recordings/models-a82e913e058618dcb30b269a54d4e6a9cb1e0017a42efe04480874fe957194d4-fb68f5a6.json
new file mode 100644
index 000000000..6558ad3c4
--- /dev/null
+++ b/tests/integration/inference/recordings/models-a82e913e058618dcb30b269a54d4e6a9cb1e0017a42efe04480874fe957194d4-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_invalid_model_error[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375165,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-b29f7386725b4f13976cd76b6dc3a278",
+ "object": "model_permission",
+ "created": 1762375165,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-bee98cb55c3b74854d0bb71b23b7e01bbb9f1580b413a26dc3afbf9da8b7d995-fb68f5a6.json b/tests/integration/inference/recordings/models-bee98cb55c3b74854d0bb71b23b7e01bbb9f1580b413a26dc3afbf9da8b7d995-fb68f5a6.json
new file mode 100644
index 000000000..dc3944bb1
--- /dev/null
+++ b/tests/integration/inference/recordings/models-bee98cb55c3b74854d0bb71b23b7e01bbb9f1580b413a26dc3afbf9da8b7d995-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_logprobs[txt=vllm/Qwen/Qwen3-0.6B-inference:completion:log_probs]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374336,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-21db8cc1a31e41eaaa4e653435618645",
+ "object": "model_permission",
+ "created": 1762374336,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-c3d9f0302c09cecba4c3797ec2d65e358910e6194e13d1001fd3567ab2eff6aa-fb68f5a6.json b/tests/integration/inference/recordings/models-c3d9f0302c09cecba4c3797ec2d65e358910e6194e13d1001fd3567ab2eff6aa-fb68f5a6.json
new file mode 100644
index 000000000..b81f6ed60
--- /dev/null
+++ b/tests/integration/inference/recordings/models-c3d9f0302c09cecba4c3797ec2d65e358910e6194e13d1001fd3567ab2eff6aa-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_different_inputs_different_outputs[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374547,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-09fed2c5660e42658ab23c6d17b7840c",
+ "object": "model_permission",
+ "created": 1762374547,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-c6e251660301fe3f503b4c31dcb551087ca9118e65b97bd894954847723a9be0-fb68f5a6.json b/tests/integration/inference/recordings/models-c6e251660301fe3f503b4c31dcb551087ca9118e65b97bd894954847723a9be0-fb68f5a6.json
new file mode 100644
index 000000000..03f377561
--- /dev/null
+++ b/tests/integration/inference/recordings/models-c6e251660301fe3f503b4c31dcb551087ca9118e65b97bd894954847723a9be0-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_completion_streaming[txt=vllm/Qwen/Qwen3-0.6B-inference:completion:sanity]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374297,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-70d68a901d2445f6b7f470c600b34c78",
+ "object": "model_permission",
+ "created": 1762374297,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-cb1f7d5cd412fddb3395ef125bbcdac95c85585f23684e71abf142004b164bbc-fb68f5a6.json b/tests/integration/inference/recordings/models-cb1f7d5cd412fddb3395ef125bbcdac95c85585f23684e71abf142004b164bbc-fb68f5a6.json
new file mode 100644
index 000000000..2d1759b41
--- /dev/null
+++ b/tests/integration/inference/recordings/models-cb1f7d5cd412fddb3395ef125bbcdac95c85585f23684e71abf142004b164bbc-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store[openai_client-txt=vllm/Qwen/Qwen3-0.6B-False]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375047,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-a8446fd6718649399402526dc6fe1477",
+ "object": "model_permission",
+ "created": 1762375047,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-cbecbec285766025f2bebca94904e63578190f33b47eb6f32cb4635a1b43e3cf-fb68f5a6.json b/tests/integration/inference/recordings/models-cbecbec285766025f2bebca94904e63578190f33b47eb6f32cb4635a1b43e3cf-fb68f5a6.json
new file mode 100644
index 000000000..bac4b8cb4
--- /dev/null
+++ b/tests/integration/inference/recordings/models-cbecbec285766025f2bebca94904e63578190f33b47eb6f32cb4635a1b43e3cf-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-True]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375254,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-f6eb51901e6443e492061deac904737c",
+ "object": "model_permission",
+ "created": 1762375254,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-d650458718dae3a10405ce1d241f0e1ceeeae8edf516cf10c611edcdf64035e3-fb68f5a6.json b/tests/integration/inference/recordings/models-d650458718dae3a10405ce1d241f0e1ceeeae8edf516cf10c611edcdf64035e3-fb68f5a6.json
new file mode 100644
index 000000000..89aef16d5
--- /dev/null
+++ b/tests/integration/inference/recordings/models-d650458718dae3a10405ce1d241f0e1ceeeae8edf516cf10c611edcdf64035e3-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming_with_n[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_02]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375279,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-31e50ba39ad84a7daa1a24a3c77dc550",
+ "object": "model_permission",
+ "created": 1762375279,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-d8acc76e3d1b54eac9754a9d3a72c571fe3078b227a257aa15afdba946b69665-fb68f5a6.json b/tests/integration/inference/recordings/models-d8acc76e3d1b54eac9754a9d3a72c571fe3078b227a257aa15afdba946b69665-fb68f5a6.json
new file mode 100644
index 000000000..a9b4bf369
--- /dev/null
+++ b/tests/integration/inference/recordings/models-d8acc76e3d1b54eac9754a9d3a72c571fe3078b227a257aa15afdba946b69665-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_streaming[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-inference:chat_completion:streaming_01]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375241,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-3ebcc379347541ea94de0f91838829e5",
+ "object": "model_permission",
+ "created": 1762375241,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-d9ff5f5ffaa7a64101936007fbe61cf2ed54f67609b54b56d92cb949234e3799-fb68f5a6.json b/tests/integration/inference/recordings/models-d9ff5f5ffaa7a64101936007fbe61cf2ed54f67609b54b56d92cb949234e3799-fb68f5a6.json
new file mode 100644
index 000000000..4bd1dde93
--- /dev/null
+++ b/tests/integration/inference/recordings/models-d9ff5f5ffaa7a64101936007fbe61cf2ed54f67609b54b56d92cb949234e3799-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_multiple_strings[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374449,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-311f880045284a469a286b8039177d10",
+ "object": "model_permission",
+ "created": 1762374449,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-da380037dc0fe8ae61b838baf268e616057e46f8424df0a9b52f94e48cef4a7f-fb68f5a6.json b/tests/integration/inference/recordings/models-da380037dc0fe8ae61b838baf268e616057e46f8424df0a9b52f94e48cef4a7f-fb68f5a6.json
new file mode 100644
index 000000000..fa5bddb15
--- /dev/null
+++ b/tests/integration/inference/recordings/models-da380037dc0fe8ae61b838baf268e616057e46f8424df0a9b52f94e48cef4a7f-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=vllm/Qwen/Qwen3-0.6B-False]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375053,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-2e52800baf7e4d3389892f33feb3f52b",
+ "object": "model_permission",
+ "created": 1762375053,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-e42ca9261e3cee9c877322a51791ab6f113478170f8a21cd0a971c53b330e999-fb68f5a6.json b/tests/integration/inference/recordings/models-e42ca9261e3cee9c877322a51791ab6f113478170f8a21cd0a971c53b330e999-fb68f5a6.json
new file mode 100644
index 000000000..5cdfadeb1
--- /dev/null
+++ b/tests/integration/inference/recordings/models-e42ca9261e3cee9c877322a51791ab6f113478170f8a21cd0a971c53b330e999-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[llama_stack_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375150,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-cfec81fed838407597a92838017f3ef5",
+ "object": "model_permission",
+ "created": 1762375150,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-e5255919e39635597ad57c723896f9d258abaad9908b22ccd03c126ce597a5db-fb68f5a6.json b/tests/integration/inference/recordings/models-e5255919e39635597ad57c723896f9d258abaad9908b22ccd03c126ce597a5db-fb68f5a6.json
new file mode 100644
index 000000000..82c9665de
--- /dev/null
+++ b/tests/integration/inference/recordings/models-e5255919e39635597ad57c723896f9d258abaad9908b22ccd03c126ce597a5db-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_encoding_format_float[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374466,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-8811d359d9724f8cac7fd6df608f69bd",
+ "object": "model_permission",
+ "created": 1762374466,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-e6664ff0c07b13aa2af6a85925f3841eef3907bc4a55f8bc352a8c960e782ada-fb68f5a6.json b/tests/integration/inference/recordings/models-e6664ff0c07b13aa2af6a85925f3841eef3907bc4a55f8bc352a8c960e782ada-fb68f5a6.json
new file mode 100644
index 000000000..f83a6dea7
--- /dev/null
+++ b/tests/integration/inference/recordings/models-e6664ff0c07b13aa2af6a85925f3841eef3907bc4a55f8bc352a8c960e782ada-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_with_dimensions[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374482,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-d4b4923adfdf40b7bd7698aa798e68eb",
+ "object": "model_permission",
+ "created": 1762374482,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-edbd3344609a0fa1e97f75ede14a094a34db0dd6cb52975abae9f6e7832c6760-fb68f5a6.json b/tests/integration/inference/recordings/models-edbd3344609a0fa1e97f75ede14a094a34db0dd6cb52975abae9f6e7832c6760-fb68f5a6.json
new file mode 100644
index 000000000..9084b4b59
--- /dev/null
+++ b/tests/integration/inference/recordings/models-edbd3344609a0fa1e97f75ede14a094a34db0dd6cb52975abae9f6e7832c6760-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-False]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375291,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-a48cfd65bcd847d7aea01d44e8add51e",
+ "object": "model_permission",
+ "created": 1762375291,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-f6a9f5d7181cf078717443564e4de54e08845224d96b9c8150fb5cfda2068e82-fb68f5a6.json b/tests/integration/inference/recordings/models-f6a9f5d7181cf078717443564e4de54e08845224d96b9c8150fb5cfda2068e82-fb68f5a6.json
new file mode 100644
index 000000000..9791dd1f7
--- /dev/null
+++ b/tests/integration/inference/recordings/models-f6a9f5d7181cf078717443564e4de54e08845224d96b9c8150fb5cfda2068e82-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_embeddings.py::test_openai_embeddings_empty_list_error[openai_client-emb=sentence-transformers/nomic-ai/nomic-embed-text-v1.5]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762374517,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-916d53706b624fefb83e5dcc699e7a69",
+ "object": "model_permission",
+ "created": 1762374517,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/inference/recordings/models-f936269fe152d95db3fb80fb10482e3cc79cfd6a28ebdf1a7a8b220ba2de641b-fb68f5a6.json b/tests/integration/inference/recordings/models-f936269fe152d95db3fb80fb10482e3cc79cfd6a28ebdf1a7a8b220ba2de641b-fb68f5a6.json
new file mode 100644
index 000000000..c561e0df0
--- /dev/null
+++ b/tests/integration/inference/recordings/models-f936269fe152d95db3fb80fb10482e3cc79cfd6a28ebdf1a7a8b220ba2de641b-fb68f5a6.json
@@ -0,0 +1,45 @@
+{
+ "test_id": "tests/integration/inference/test_openai_completion.py::test_inference_store[client_with_models-txt=vllm/Qwen/Qwen3-0.6B-False]",
+ "request": {
+ "method": "POST",
+ "url": "http://localhost:8000/v1/v1/models",
+ "headers": {},
+ "body": {},
+ "endpoint": "/v1/models",
+ "model": ""
+ },
+ "response": {
+ "body": [
+ {
+ "__type__": "openai.types.model.Model",
+ "__data__": {
+ "id": "Qwen/Qwen3-0.6B",
+ "created": 1762375285,
+ "object": "model",
+ "owned_by": "vllm",
+ "root": "/root/.cache/Qwen3-0.6B",
+ "parent": null,
+ "max_model_len": 8192,
+ "permission": [
+ {
+ "id": "modelperm-e0640be42b814b3394545ebe92d844b3",
+ "object": "model_permission",
+ "created": 1762375285,
+ "allow_create_engine": false,
+ "allow_sampling": true,
+ "allow_logprobs": true,
+ "allow_search_indices": false,
+ "allow_view": true,
+ "allow_fine_tuning": false,
+ "organization": "*",
+ "group": null,
+ "is_blocking": false
+ }
+ ]
+ }
+ }
+ ],
+ "is_streaming": false
+ },
+ "id_normalization_mapping": {}
+}
diff --git a/tests/integration/suites.py b/tests/integration/suites.py
index e1fb6a1c7..0cec66afe 100644
--- a/tests/integration/suites.py
+++ b/tests/integration/suites.py
@@ -78,7 +78,7 @@ SETUP_DEFINITIONS: dict[str, Setup] = {
"VLLM_URL": "http://localhost:8000/v1",
},
defaults={
- "text_model": "vllm/meta-llama/Llama-3.2-1B-Instruct",
+ "text_model": "vllm/Qwen/Qwen3-0.6B",
"embedding_model": "sentence-transformers/nomic-embed-text-v1.5",
},
),
@@ -169,6 +169,11 @@ SUITE_DEFINITIONS: dict[str, Suite] = {
roots=base_roots,
default_setup="ollama",
),
+ "base-vllm-subset": Suite(
+ name="base-vllm-subset",
+ roots=["tests/integration/inference"],
+ default_setup="vllm",
+ ),
"responses": Suite(
name="responses",
roots=["tests/integration/responses"],