Merge branch 'main' into responses_object

tests/README.md

@@ -38,26 +38,15 @@ For running integration tests, you must provide a few things:
   - a distribution name (e.g., `starter`) or a path to a `run.yaml` file
   - a comma-separated list of api=provider pairs, e.g. `inference=fireworks,safety=llama-guard,agents=meta-reference`. This is most useful for testing a single API surface.
 
-- Whether you are using replay or live mode for inference. This is specified with the LLAMA_STACK_TEST_INFERENCE_MODE environment variable. The default mode currently is "live" -- that is certainly surprising, but we will fix this soon.
-
 - Any API keys you need to use should be set in the environment, or can be passed in with the --env option.
 
 You can run the integration tests in replay mode with:
 ```bash
 # Run all tests with existing recordings
-LLAMA_STACK_TEST_INFERENCE_MODE=replay \
-  LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings \
   uv run --group test \
   pytest -sv tests/integration/ --stack-config=starter
 ```
 
-If you don't specify LLAMA_STACK_TEST_INFERENCE_MODE, by default it will be in "live" mode -- that is, it will make real API calls.
-
-```bash
-# Test against live APIs
-FIREWORKS_API_KEY=your_key pytest -sv tests/integration/inference --stack-config=starter
-```
-
 ### Re-recording tests
 
 #### Local Re-recording (Manual Setup Required)
@@ -66,7 +55,6 @@ If you want to re-record tests locally, you can do so with:
 
 ```bash
 LLAMA_STACK_TEST_INFERENCE_MODE=record \
-  LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings \
   uv run --group test \
   pytest -sv tests/integration/ --stack-config=starter -k "<appropriate test name>"
 ```
@@ -89,7 +77,7 @@ You must be careful when re-recording. CI workflows assume a specific setup for
 ./scripts/github/schedule-record-workflow.sh --test-subdirs "agents,inference"
 
 # Record with vision tests enabled
-./scripts/github/schedule-record-workflow.sh --test-subdirs "inference" --run-vision-tests
+./scripts/github/schedule-record-workflow.sh --test-suite vision
 
 # Record with specific provider
 ./scripts/github/schedule-record-workflow.sh --test-subdirs "agents" --test-provider vllm

tests/integration/README.md

@@ -6,9 +6,7 @@ Integration tests verify complete workflows across different providers using Lla
 
 ```bash
 # Run all integration tests with existing recordings
-LLAMA_STACK_TEST_INFERENCE_MODE=replay \
-  LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings \
-  uv run --group test \
+uv run --group test \
   pytest -sv tests/integration/ --stack-config=starter
 ```
 
@@ -42,6 +40,37 @@ Model parameters can be influenced by the following options:
 Each of these are comma-separated lists and can be used to generate multiple parameter combinations. Note that tests will be skipped
 if no model is specified.
 
+### Suites and Setups
+
+- `--suite`: single named suite that narrows which tests are collected.
+- Available suites:
+  - `base`: collects most tests (excludes responses and post_training)
+  - `responses`: collects tests under `tests/integration/responses` (needs strong tool-calling models)
+  - `vision`: collects only `tests/integration/inference/test_vision_inference.py`
+- `--setup`: global configuration that can be used with any suite. Setups prefill model/env defaults; explicit CLI flags always win.
+  - Available setups:
+    - `ollama`: Local Ollama provider with lightweight models (sets OLLAMA_URL, uses llama3.2:3b-instruct-fp16)
+    - `vllm`: VLLM provider for efficient local inference (sets VLLM_URL, uses Llama-3.2-1B-Instruct)
+    - `gpt`: OpenAI GPT models for high-quality responses (uses gpt-4o)
+    - `claude`: Anthropic Claude models for high-quality responses (uses claude-3-5-sonnet)
+
+Examples
+
+```bash
+# Fast responses run with a strong tool-calling model
+pytest -s -v tests/integration --stack-config=server:starter --suite=responses --setup=gpt
+
+# Fast single-file vision run with Ollama defaults
+pytest -s -v tests/integration --stack-config=server:starter --suite=vision --setup=ollama
+
+# Base suite with VLLM for performance
+pytest -s -v tests/integration --stack-config=server:starter --suite=base --setup=vllm
+
+# Override a default from setup
+pytest -s -v tests/integration --stack-config=server:starter \
+  --suite=responses --setup=gpt --embedding-model=text-embedding-3-small
+```
+
 ## Examples
 
 ### Testing against a Server
@@ -98,29 +127,24 @@ pytest -s -v tests/integration/vector_io/ \
 
 The testing system supports three modes controlled by environment variables:
 
-### LIVE Mode (Default)
-Tests make real API calls:
+### REPLAY Mode (Default)
+Uses cached responses instead of making API calls:
 ```bash
-LLAMA_STACK_TEST_INFERENCE_MODE=live pytest tests/integration/
+pytest tests/integration/
 ```
-
 ### RECORD Mode
 Captures API interactions for later replay:
 ```bash
-LLAMA_STACK_TEST_INFERENCE_MODE=record \
-LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings \
-pytest tests/integration/inference/test_new_feature.py
+pytest tests/integration/inference/test_new_feature.py --inference-mode=record
 ```
 
-### REPLAY Mode
-Uses cached responses instead of making API calls:
+### LIVE Mode
+Tests make real API calls (but not recorded):
 ```bash
-LLAMA_STACK_TEST_INFERENCE_MODE=replay \
-LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings \
-pytest tests/integration/
+pytest tests/integration/ --inference-mode=live
 ```
 
-Note that right now you must specify the recording directory. This is because different tests use different recording directories and we don't (yet) have a fool-proof way to map a test to a recording directory. We are working on this.
+By default, the recording directory is `tests/integration/recordings`. You can override this by setting the `LLAMA_STACK_TEST_RECORDING_DIR` environment variable.
 
 ## Managing Recordings
 
@@ -138,16 +162,14 @@ cat recordings/responses/abc123.json | jq '.'
 #### Remote Re-recording (Recommended)
 Use the automated workflow script for easier re-recording:
 ```bash
-./scripts/github/schedule-record-workflow.sh --test-subdirs "inference,agents"
+./scripts/github/schedule-record-workflow.sh --subdirs "inference,agents"
 ```
 See the [main testing guide](../README.md#remote-re-recording-recommended) for full details.
 
 #### Local Re-recording
 ```bash
 # Re-record specific tests
-LLAMA_STACK_TEST_INFERENCE_MODE=record \
-LLAMA_STACK_TEST_RECORDING_DIR=tests/integration/recordings \
-pytest -s -v --stack-config=server:starter tests/integration/inference/test_modified.py
+pytest -s -v --stack-config=server:starter tests/integration/inference/test_modified.py --inference-mode=record
 ```
 
 Note that when re-recording tests, you must use a Stack pointing to a server (i.e., `server:starter`). This subtlety exists because the set of tests run in server are a superset of the set of tests run in the library client.

tests/integration/batches/test_batches.py

@@ -268,3 +268,58 @@ class TestBatchesIntegration:
 
         deleted_error_file = openai_client.files.delete(final_batch.error_file_id)
         assert deleted_error_file.deleted, f"Error file {final_batch.error_file_id} was not deleted successfully"
+
+    def test_batch_e2e_completions(self, openai_client, batch_helper, text_model_id):
+        """Run an end-to-end batch with a single successful text completion request."""
+        request_body = {"model": text_model_id, "prompt": "Say completions", "max_tokens": 20}
+
+        batch_requests = [
+            {
+                "custom_id": "success-1",
+                "method": "POST",
+                "url": "/v1/completions",
+                "body": request_body,
+            }
+        ]
+
+        with batch_helper.create_file(batch_requests) as uploaded_file:
+            batch = openai_client.batches.create(
+                input_file_id=uploaded_file.id,
+                endpoint="/v1/completions",
+                completion_window="24h",
+                metadata={"test": "e2e_completions_success"},
+            )
+
+            final_batch = batch_helper.wait_for(
+                batch.id,
+                max_wait_time=3 * 60,
+                expected_statuses={"completed"},
+                timeout_action="skip",
+            )
+
+        assert final_batch.status == "completed"
+        assert final_batch.request_counts is not None
+        assert final_batch.request_counts.total == 1
+        assert final_batch.request_counts.completed == 1
+        assert final_batch.output_file_id is not None
+
+        output_content = openai_client.files.content(final_batch.output_file_id)
+        if isinstance(output_content, str):
+            output_text = output_content
+        else:
+            output_text = output_content.content.decode("utf-8")
+
+        output_lines = output_text.strip().split("\n")
+        assert len(output_lines) == 1
+
+        result = json.loads(output_lines[0])
+        assert result["custom_id"] == "success-1"
+        assert "response" in result
+        assert result["response"]["status_code"] == 200
+
+        deleted_output_file = openai_client.files.delete(final_batch.output_file_id)
+        assert deleted_output_file.deleted
+
+        if final_batch.error_file_id is not None:
+            deleted_error_file = openai_client.files.delete(final_batch.error_file_id)
+            assert deleted_error_file.deleted

tests/integration/conftest.py

@@ -6,15 +6,17 @@
 import inspect
 import itertools
 import os
-import platform
 import textwrap
 import time
+from pathlib import Path
 
 import pytest
 from dotenv import load_dotenv
 
 from llama_stack.log import get_logger
 
+from .suites import SETUP_DEFINITIONS, SUITE_DEFINITIONS
+
 logger = get_logger(__name__, category="tests")
 
 
@@ -30,6 +32,8 @@ def pytest_runtest_makereport(item, call):
 def pytest_sessionstart(session):
     # stop macOS from complaining about duplicate OpenMP libraries
     os.environ["KMP_DUPLICATE_LIB_OK"] = "TRUE"
+    if "LLAMA_STACK_TEST_INFERENCE_MODE" not in os.environ:
+        os.environ["LLAMA_STACK_TEST_INFERENCE_MODE"] = "replay"
 
 
 def pytest_runtest_teardown(item):
@@ -59,9 +63,36 @@ def pytest_configure(config):
         key, value = env_var.split("=", 1)
         os.environ[key] = value
 
-    if platform.system() == "Darwin":  # Darwin is the system name for macOS
-        os.environ["DISABLE_CODE_SANDBOX"] = "1"
-        logger.info("Setting DISABLE_CODE_SANDBOX=1 for macOS")
+    inference_mode = config.getoption("--inference-mode")
+    os.environ["LLAMA_STACK_TEST_INFERENCE_MODE"] = inference_mode
+
+    suite = config.getoption("--suite")
+    if suite:
+        if suite not in SUITE_DEFINITIONS:
+            raise pytest.UsageError(f"Unknown suite: {suite}. Available: {', '.join(sorted(SUITE_DEFINITIONS.keys()))}")
+
+    # Apply setups (global parameterizations): env + defaults
+    setup = config.getoption("--setup")
+    if suite and not setup:
+        setup = SUITE_DEFINITIONS[suite].default_setup
+
+    if setup:
+        if setup not in SETUP_DEFINITIONS:
+            raise pytest.UsageError(
+                f"Unknown setup '{setup}'. Available: {', '.join(sorted(SETUP_DEFINITIONS.keys()))}"
+            )
+
+        setup_obj = SETUP_DEFINITIONS[setup]
+        logger.info(f"Applying setup '{setup}'{' for suite ' + suite if suite else ''}")
+        # Apply env first
+        for k, v in setup_obj.env.items():
+            if k not in os.environ:
+                os.environ[k] = str(v)
+        # Apply defaults if not provided explicitly
+        for dest, value in setup_obj.defaults.items():
+            current = getattr(config.option, dest, None)
+            if not current:
+                setattr(config.option, dest, value)
 
 
 def pytest_addoption(parser):
@@ -103,16 +134,32 @@ def pytest_addoption(parser):
         default=384,
         help="Output dimensionality of the embedding model to use for testing. Default: 384",
     )
+
     parser.addoption(
-        "--record-responses",
-        action="store_true",
-        help="Record new API responses instead of using cached ones.",
+        "--inference-mode",
+        help="Inference mode: { record, replay, live } (default: replay)",
+        choices=["record", "replay", "live"],
+        default="replay",
     )
     parser.addoption(
         "--report",
         help="Path where the test report should be written, e.g. --report=/path/to/report.md",
     )
 
+    available_suites = ", ".join(sorted(SUITE_DEFINITIONS.keys()))
+    suite_help = (
+        f"Single test suite to run (narrows collection). Available: {available_suites}. Example: --suite=responses"
+    )
+    parser.addoption("--suite", help=suite_help)
+
+    # Global setups for any suite
+    available_setups = ", ".join(sorted(SETUP_DEFINITIONS.keys()))
+    setup_help = (
+        f"Global test setup configuration. Available: {available_setups}. "
+        "Can be used with any suite. Example: --setup=ollama"
+    )
+    parser.addoption("--setup", help=setup_help)
+
 
 MODEL_SHORT_IDS = {
     "meta-llama/Llama-3.2-3B-Instruct": "3B",
@@ -195,3 +242,36 @@ def pytest_generate_tests(metafunc):
 
 
 pytest_plugins = ["tests.integration.fixtures.common"]
+
+
+def pytest_ignore_collect(path: str, config: pytest.Config) -> bool:
+    """Skip collecting paths outside the selected suite roots for speed."""
+    suite = config.getoption("--suite")
+    if not suite:
+        return False
+
+    sobj = SUITE_DEFINITIONS.get(suite)
+    roots: list[str] = sobj.get("roots", []) if isinstance(sobj, dict) else getattr(sobj, "roots", [])
+    if not roots:
+        return False
+
+    p = Path(str(path)).resolve()
+
+    # Only constrain within tests/integration to avoid ignoring unrelated tests
+    integration_root = (Path(str(config.rootpath)) / "tests" / "integration").resolve()
+    if not p.is_relative_to(integration_root):
+        return False
+
+    for r in roots:
+        rp = (Path(str(config.rootpath)) / r).resolve()
+        if rp.is_file():
+            # Allow the exact file and any ancestor directories so pytest can walk into it.
+            if p == rp:
+                return False
+            if p.is_dir() and rp.is_relative_to(p):
+                return False
+        else:
+            # Allow anything inside an allowed directory
+            if p.is_relative_to(rp):
+                return False
+    return True

tests/integration/files/test_files.py

@@ -8,6 +8,7 @@ from io import BytesIO
 from unittest.mock import patch
 
 import pytest
+import requests
 
 from llama_stack.core.datatypes import User
 
@@ -79,6 +80,88 @@ def test_openai_client_basic_operations(openai_client):
                 pass  # ignore 404
 
 
+@pytest.mark.xfail(message="expires_after not available on all providers")
+def test_expires_after(openai_client):
+    """Test uploading a file with expires_after parameter."""
+    client = openai_client
+
+    uploaded_file = None
+    try:
+        with BytesIO(b"expires_after test") as file_buffer:
+            file_buffer.name = "expires_after.txt"
+            uploaded_file = client.files.create(
+                file=file_buffer,
+                purpose="assistants",
+                expires_after={"anchor": "created_at", "seconds": 4545},
+            )
+
+        assert uploaded_file.expires_at is not None
+        assert uploaded_file.expires_at == uploaded_file.created_at + 4545
+
+        listed = client.files.list()
+        ids = [f.id for f in listed.data]
+        assert uploaded_file.id in ids
+
+        retrieved = client.files.retrieve(uploaded_file.id)
+        assert retrieved.id == uploaded_file.id
+
+    finally:
+        if uploaded_file is not None:
+            try:
+                client.files.delete(uploaded_file.id)
+            except Exception:
+                pass
+
+
+@pytest.mark.xfail(message="expires_after not available on all providers")
+def test_expires_after_requests(openai_client):
+    """Upload a file using requests multipart/form-data and bracketed expires_after fields.
+
+    This ensures clients that send form fields like `expires_after[anchor]` and
+    `expires_after[seconds]` are handled by the server.
+    """
+    base_url = f"{openai_client.base_url}files"
+
+    uploaded_id = None
+    try:
+        files = {"file": ("expires_after_with_requests.txt", BytesIO(b"expires_after via requests"))}
+        data = {
+            "purpose": "assistants",
+            "expires_after[anchor]": "created_at",
+            "expires_after[seconds]": "4545",
+        }
+
+        session = requests.Session()
+        request = requests.Request("POST", base_url, files=files, data=data)
+        prepared = session.prepare_request(request)
+        resp = session.send(prepared, timeout=30)
+        resp.raise_for_status()
+        result = resp.json()
+
+        assert result.get("id", "").startswith("file-")
+        uploaded_id = result["id"]
+        assert result.get("created_at") is not None
+        assert result.get("expires_at") == result["created_at"] + 4545
+
+        list_resp = requests.get(base_url, timeout=30)
+        list_resp.raise_for_status()
+        listed = list_resp.json()
+        ids = [f["id"] for f in listed.get("data", [])]
+        assert uploaded_id in ids
+
+        retrieve_resp = requests.get(f"{base_url}/{uploaded_id}", timeout=30)
+        retrieve_resp.raise_for_status()
+        retrieved = retrieve_resp.json()
+        assert retrieved["id"] == uploaded_id
+
+    finally:
+        if uploaded_id:
+            try:
+                requests.delete(f"{base_url}/{uploaded_id}", timeout=30)
+            except Exception:
+                pass
+
+
 @pytest.mark.xfail(message="User isolation broken for current providers, must be fixed.")
 @patch("llama_stack.providers.utils.sqlstore.authorized_sqlstore.get_authenticated_user")
 def test_files_authentication_isolation(mock_get_authenticated_user, llama_stack_client):

tests/integration/inference/test_openai_completion.py

@@ -5,11 +5,26 @@
 # the root directory of this source tree.
 
 
+import time
+import unicodedata
+
 import pytest
 
 from ..test_cases.test_case import TestCase
 
 
+def _normalize_text(text: str) -> str:
+    """
+    Normalize Unicode text by removing diacritical marks for comparison.
+
+    The test case streaming_01 expects the answer "Sol" for the question "What's the name of the Sun
+    in latin?", but the model is returning "sōl" (with a macron over the 'o'), which is the correct
+    Latin spelling. The test is failing because it's doing a simple case-insensitive string search
+    for "sol" but the actual response contains the diacritical mark.
+    """
+    return unicodedata.normalize("NFD", text).encode("ascii", "ignore").decode("ascii").lower()
+
+
 def provider_from_model(client_with_models, model_id):
     models = {m.identifier: m for m in client_with_models.models.list()}
     models.update({m.provider_resource_id: m for m in client_with_models.models.list()})
@@ -33,8 +48,17 @@ def skip_if_model_doesnt_support_openai_completion(client_with_models, model_id)
         "remote::nvidia",
         "remote::runpod",
         "remote::sambanova",
-        "remote::tgi",
         "remote::vertexai",
+        # {"error":{"message":"Unknown request URL: GET /openai/v1/completions. Please check the URL for typos,
+        # or see the docs at https://console.groq.com/docs/","type":"invalid_request_error","code":"unknown_url"}}
+        "remote::groq",
+        "remote::gemini",  # https://generativelanguage.googleapis.com/v1beta/openai/completions -> 404
+        "remote::anthropic",  # at least claude-3-{5,7}-{haiku,sonnet}-* / claude-{sonnet,opus}-4-* are not supported
+        "remote::azure",  # {'error': {'code': 'OperationNotSupported', 'message': 'The completion operation
+        #  does not work with the specified model, gpt-5-mini. Please choose different model and try
+        #  again. You can learn more about which models can be used with each operation here:
+        #  https://go.microsoft.com/fwlink/?linkid=2197993.'}}"}
+        "remote::watsonx",  # return 404 when hitting the /openai/v1 endpoint
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI completions.")
 
@@ -56,6 +80,28 @@ def skip_if_model_doesnt_support_suffix(client_with_models, model_id):
         pytest.skip(f"Provider {provider.provider_type} doesn't support suffix.")
 
 
+def skip_if_doesnt_support_n(client_with_models, model_id):
+    provider = provider_from_model(client_with_models, model_id)
+    if provider.provider_type in (
+        "remote::sambanova",
+        "remote::ollama",
+        # https://console.groq.com/docs/openai#currently-unsupported-openai-features
+        # -> Error code: 400 - {'error': {'message': "'n' : number must be at most 1", 'type': 'invalid_request_error'}}
+        "remote::groq",
+        # Error code: 400 - [{'error': {'code': 400, 'message': 'Only one candidate can be specified in the
+        # current model', 'status': 'INVALID_ARGUMENT'}}]
+        "remote::gemini",
+        # https://docs.anthropic.com/en/api/openai-sdk#simple-fields
+        "remote::anthropic",
+        "remote::vertexai",
+        #  Error code: 400 - [{'error': {'code': 400, 'message': 'Unable to submit request because candidateCount must be 1 but
+        #  the entered value was 2. Update the candidateCount value and try again.', 'status': 'INVALID_ARGUMENT'}
+        "remote::tgi",  # TGI ignores n param silently
+        "remote::together",  # `n` > 1 is not supported when streaming tokens. Please disable `stream`
+    ):
+        pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support n param.")
+
+
 def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, model_id):
     provider = provider_from_model(client_with_models, model_id)
     if provider.provider_type in (
@@ -66,7 +112,7 @@ def skip_if_model_doesnt_support_openai_chat_completion(client_with_models, mode
         "remote::cerebras",
         "remote::databricks",
         "remote::runpod",
-        "remote::tgi",
+        "remote::watsonx",  # watsonx returns 404 when hitting the /openai/v1 endpoint
     ):
         pytest.skip(f"Model {model_id} hosted by {provider.provider_type} doesn't support OpenAI chat completions.")
 
@@ -130,7 +176,8 @@ def test_openai_completion_non_streaming_suffix(llama_stack_client, client_with_
     assert len(response.choices) > 0
     choice = response.choices[0]
     assert len(choice.text) > 5
-    assert "france" in choice.text.lower()
+    normalized_text = _normalize_text(choice.text)
+    assert "france" in normalized_text
 
 
 @pytest.mark.parametrize(
@@ -221,7 +268,9 @@ def test_openai_chat_completion_non_streaming(compat_client, client_with_models,
     )
     message_content = response.choices[0].message.content.lower().strip()
     assert len(message_content) > 0
-    assert expected.lower() in message_content
+    normalized_expected = _normalize_text(expected)
+    normalized_content = _normalize_text(message_content)
+    assert normalized_expected in normalized_content
 
 
 @pytest.mark.parametrize(
@@ -245,10 +294,13 @@ def test_openai_chat_completion_streaming(compat_client, client_with_models, tex
     )
     streamed_content = []
     for chunk in response:
-        if chunk.choices[0].delta.content:
+        # On some providers like Azure, the choices are empty on the first chunk, so we need to check for that
+        if chunk.choices and len(chunk.choices) > 0 and chunk.choices[0].delta.content:
             streamed_content.append(chunk.choices[0].delta.content.lower().strip())
     assert len(streamed_content) > 0
-    assert expected.lower() in "".join(streamed_content)
+    normalized_expected = _normalize_text(expected)
+    normalized_content = _normalize_text("".join(streamed_content))
+    assert normalized_expected in normalized_content
 
 
 @pytest.mark.parametrize(
@@ -260,10 +312,7 @@ def test_openai_chat_completion_streaming(compat_client, client_with_models, tex
 )
 def test_openai_chat_completion_streaming_with_n(compat_client, client_with_models, text_model_id, test_case):
     skip_if_model_doesnt_support_openai_chat_completion(client_with_models, text_model_id)
-
-    provider = provider_from_model(client_with_models, text_model_id)
-    if provider.provider_type == "remote::ollama":
-        pytest.skip(f"Model {text_model_id} hosted by {provider.provider_type} doesn't support n > 1.")
+    skip_if_doesnt_support_n(client_with_models, text_model_id)
 
     tc = TestCase(test_case)
     question = tc["question"]
@@ -284,8 +333,12 @@ def test_openai_chat_completion_streaming_with_n(compat_client, client_with_mode
                     streamed_content.get(choice.index, "") + choice.delta.content.lower().strip()
                 )
     assert len(streamed_content) == 2
+    normalized_expected = _normalize_text(expected)
     for i, content in streamed_content.items():
-        assert expected.lower() in content, f"Choice {i}: Expected {expected.lower()} in {content}"
+        normalized_content = _normalize_text(content)
+        assert normalized_expected in normalized_content, (
+            f"Choice {i}: Expected {normalized_expected} in {normalized_content}"
+        )
 
 
 @pytest.mark.parametrize(
@@ -315,16 +368,23 @@ def test_inference_store(compat_client, client_with_models, text_model_id, strea
         content = ""
         response_id = None
         for chunk in response:
-            if response_id is None:
+            if response_id is None and chunk.id:
                 response_id = chunk.id
-            if chunk.choices[0].delta.content:
+            if chunk.choices and len(chunk.choices) > 0 and chunk.choices[0].delta.content:
                 content += chunk.choices[0].delta.content
     else:
         response_id = response.id
         content = response.choices[0].message.content
 
-    responses = client.chat.completions.list(limit=1000)
-    assert response_id in [r.id for r in responses.data]
+    tries = 0
+    while tries < 10:
+        responses = client.chat.completions.list(limit=1000)
+        if response_id in [r.id for r in responses.data]:
+            break
+        else:
+            tries += 1
+            time.sleep(0.1)
+    assert tries < 10, f"Response {response_id} not found after 1 second"
 
     retrieved_response = client.chat.completions.retrieve(response_id)
     assert retrieved_response.id == response_id
@@ -379,15 +439,28 @@ def test_inference_store_tool_calls(compat_client, client_with_models, text_mode
         content = ""
         response_id = None
         for chunk in response:
-            if response_id is None:
+            if response_id is None and chunk.id:
                 response_id = chunk.id
-            if delta := chunk.choices[0].delta:
-                if delta.content:
-                    content += delta.content
+            if chunk.choices and len(chunk.choices) > 0:
+                if delta := chunk.choices[0].delta:
+                    if delta.content:
+                        content += delta.content
     else:
         response_id = response.id
         content = response.choices[0].message.content
 
+    # wait for the response to be stored
+    tries = 0
+    while tries < 10:
+        responses = client.chat.completions.list(limit=1000)
+        if response_id in [r.id for r in responses.data]:
+            break
+        else:
+            tries += 1
+            time.sleep(0.1)
+
+    assert tries < 10, f"Response {response_id} not found after 1 second"
+
     responses = client.chat.completions.list(limit=1000)
     assert response_id in [r.id for r in responses.data]
 
@@ -441,4 +514,5 @@ def test_openai_chat_completion_non_streaming_with_file(openai_client, client_wi
         stream=False,
     )
     message_content = response.choices[0].message.content.lower().strip()
-    assert "hello world" in message_content
+    normalized_content = _normalize_text(message_content)
+    assert "hello world" in normalized_content

tests/integration/inference/test_openai_embeddings.py

@@ -29,9 +29,35 @@ def provider_from_model(client_with_models, model_id):
     return providers[provider_id]
 
 
-def skip_if_model_doesnt_support_variable_dimensions(model_id):
-    if "text-embedding-3" not in model_id:
-        pytest.skip("{model_id} does not support variable output embedding dimensions")
+def skip_if_model_doesnt_support_user_param(client, model_id):
+    provider = provider_from_model(client, model_id)
+    if provider.provider_type in (
+        "remote::together",  # service returns 400
+    ):
+        pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support user param.")
+
+
+def skip_if_model_doesnt_support_encoding_format_base64(client, model_id):
+    provider = provider_from_model(client, model_id)
+    if provider.provider_type in (
+        "remote::together",  # param silently ignored, always returns floats
+    ):
+        pytest.skip(f"Model {model_id} hosted by {provider.provider_type} does not support encoding_format='base64'.")
+
+
+def skip_if_model_doesnt_support_variable_dimensions(client_with_models, model_id):
+    provider = provider_from_model(client_with_models, model_id)
+    if provider.provider_type in (
+        "remote::together",  # returns 400
+        "inline::sentence-transformers",
+    ):
+        pytest.skip(
+            f"Model {model_id} hosted by {provider.provider_type} does not support variable output embedding dimensions."
+        )
+    if provider.provider_type == "remote::openai" and "text-embedding-3" not in model_id:
+        pytest.skip(
+            f"Model {model_id} hosted by {provider.provider_type} does not support variable output embedding dimensions."
+        )
 
 
 @pytest.fixture(params=["openai_client", "llama_stack_client"])
@@ -92,6 +118,7 @@ def test_openai_embeddings_multiple_strings(compat_client, client_with_models, e
     response = compat_client.embeddings.create(
         model=embedding_model_id,
         input=input_texts,
+        encoding_format="float",
     )
 
     assert response.object == "list"
@@ -127,7 +154,7 @@ def test_openai_embeddings_with_encoding_format_float(compat_client, client_with
 def test_openai_embeddings_with_dimensions(compat_client, client_with_models, embedding_model_id):
     """Test OpenAI embeddings endpoint with custom dimensions parameter."""
     skip_if_model_doesnt_support_openai_embeddings(client_with_models, embedding_model_id)
-    skip_if_model_doesnt_support_variable_dimensions(embedding_model_id)
+    skip_if_model_doesnt_support_variable_dimensions(client_with_models, embedding_model_id)
 
     input_text = "Test dimensions parameter"
     dimensions = 16
@@ -148,6 +175,7 @@ def test_openai_embeddings_with_dimensions(compat_client, client_with_models, em
 def test_openai_embeddings_with_user_parameter(compat_client, client_with_models, embedding_model_id):
     """Test OpenAI embeddings endpoint with user parameter."""
     skip_if_model_doesnt_support_openai_embeddings(client_with_models, embedding_model_id)
+    skip_if_model_doesnt_support_user_param(client_with_models, embedding_model_id)
 
     input_text = "Test user parameter"
     user_id = "test-user-123"
@@ -196,11 +224,13 @@ def test_openai_embeddings_different_inputs_different_outputs(compat_client, cli
     response1 = compat_client.embeddings.create(
         model=embedding_model_id,
         input=input_text1,
+        encoding_format="float",
     )
 
     response2 = compat_client.embeddings.create(
         model=embedding_model_id,
         input=input_text2,
+        encoding_format="float",
     )
 
     embedding1 = response1.data[0].embedding
@@ -214,7 +244,8 @@ def test_openai_embeddings_different_inputs_different_outputs(compat_client, cli
 def test_openai_embeddings_with_encoding_format_base64(compat_client, client_with_models, embedding_model_id):
     """Test OpenAI embeddings endpoint with base64 encoding format."""
     skip_if_model_doesnt_support_openai_embeddings(client_with_models, embedding_model_id)
-    skip_if_model_doesnt_support_variable_dimensions(embedding_model_id)
+    skip_if_model_doesnt_support_encoding_format_base64(client_with_models, embedding_model_id)
+    skip_if_model_doesnt_support_variable_dimensions(client_with_models, embedding_model_id)
 
     input_text = "Test base64 encoding format"
     dimensions = 12
@@ -247,6 +278,7 @@ def test_openai_embeddings_with_encoding_format_base64(compat_client, client_wit
 def test_openai_embeddings_base64_batch_processing(compat_client, client_with_models, embedding_model_id):
     """Test OpenAI embeddings endpoint with base64 encoding for batch processing."""
     skip_if_model_doesnt_support_openai_embeddings(client_with_models, embedding_model_id)
+    skip_if_model_doesnt_support_encoding_format_base64(client_with_models, embedding_model_id)
 
     input_texts = ["First text for base64", "Second text for base64", "Third text for base64"]
 

tests/integration/inference/test_text_inference.py

@@ -32,6 +32,7 @@ def skip_if_model_doesnt_support_completion(client_with_models, model_id):
             "remote::vertexai",
             "remote::groq",
             "remote::sambanova",
+            "remote::azure",
         )
         or "openai-compat" in provider.provider_type
     ):
@@ -44,7 +45,7 @@ def skip_if_model_doesnt_support_json_schema_structured_output(client_with_model
     provider_id = models[model_id].provider_id
     providers = {p.provider_id: p for p in client_with_models.providers.list()}
     provider = providers[provider_id]
-    if provider.provider_type in ("remote::sambanova",):
+    if provider.provider_type in ("remote::sambanova", "remote::azure", "remote::watsonx"):
         pytest.skip(
             f"Model {model_id} hosted by {provider.provider_type} doesn't support json_schema structured output"
         )
@@ -210,6 +211,7 @@ def test_text_completion_log_probs_streaming(client_with_models, text_model_id,
 )
 def test_text_completion_structured_output(client_with_models, text_model_id, test_case):
     skip_if_model_doesnt_support_completion(client_with_models, text_model_id)
+    skip_if_model_doesnt_support_json_schema_structured_output(client_with_models, text_model_id)
 
     class AnswerFormat(BaseModel):
         name: str

tests/integration/recordings/responses/00ba04f74a96.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:53.860911Z",
+        "created_at": "2025-09-03T17:37:35.23084Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 249137667,
-        "load_duration": 152509542,
+        "total_duration": 195981375,
+        "load_duration": 110522917,
         "prompt_eval_count": 216,
-        "prompt_eval_duration": 71000000,
+        "prompt_eval_duration": 72393958,
         "eval_count": 2,
-        "eval_duration": 24000000,
+        "eval_duration": 11843000,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/04172112ffbb.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:18.033900164Z",
+          "created_at": "2025-09-03T17:41:43.950283Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:18.213371151Z",
+          "created_at": "2025-09-03T17:41:43.991122Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:18.387513976Z",
+          "created_at": "2025-09-03T17:41:44.031378Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:18.564344287Z",
+          "created_at": "2025-09-03T17:41:44.073098Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:18.746579415Z",
+          "created_at": "2025-09-03T17:41:44.115961Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:18.923276047Z",
+          "created_at": "2025-09-03T17:41:44.156517Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:19.099961963Z",
+          "created_at": "2025-09-03T17:41:44.197079Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:19.275621884Z",
+          "created_at": "2025-09-03T17:41:44.237565Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:19.452204196Z",
+          "created_at": "2025-09-03T17:41:44.277755Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:19.626937514Z",
+          "created_at": "2025-09-03T17:41:44.318476Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,7 +201,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:19.805566767Z",
+          "created_at": "2025-09-03T17:41:44.358628Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -219,7 +219,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:19.985987477Z",
+          "created_at": "2025-09-03T17:41:44.398984Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -237,7 +237,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:20.166458601Z",
+          "created_at": "2025-09-03T17:41:44.439232Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -255,7 +255,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:20.343346795Z",
+          "created_at": "2025-09-03T17:41:44.479478Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -273,7 +273,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:20.525008091Z",
+          "created_at": "2025-09-03T17:41:44.520202Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -291,7 +291,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:20.709087695Z",
+          "created_at": "2025-09-03T17:41:44.560517Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -309,7 +309,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:20.887074305Z",
+          "created_at": "2025-09-03T17:41:44.601592Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -327,15 +327,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:21.065244925Z",
+          "created_at": "2025-09-03T17:41:44.642064Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 4373531496,
-          "load_duration": 44438132,
+          "total_duration": 887142667,
+          "load_duration": 119331417,
           "prompt_eval_count": 56,
-          "prompt_eval_duration": 1296273199,
+          "prompt_eval_duration": 74294709,
           "eval_count": 18,
-          "eval_duration": 3032321735,
+          "eval_duration": 692842791,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/07c5fa34d9ca.json

@@ -0,0 +1,800 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "togethercomputer/m2-bert-80M-32k-retrieval",
+      "input": "Test encoding format"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "togethercomputer/m2-bert-80M-32k-retrieval"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.011256923,
+              0.0037174695,
+              0.047607094,
+              -0.03605117,
+              0.022678856,
+              0.0022196341,
+              0.008172763,
+              -0.07876377,
+              -0.012652523,
+              -0.124776885,
+              -0.07201225,
+              0.011470616,
+              0.020233244,
+              -0.03953407,
+              0.017867543,
+              -0.07615726,
+              0.015161683,
+              0.01493531,
+              0.0021282644,
+              0.02805457,
+              0.0008320583,
+              0.022922216,
+              0.049158294,
+              -0.03197842,
+              0.020910429,
+              0.03798574,
+              0.032469492,
+              0.009267314,
+              0.0883011,
+              0.0032435523,
+              0.013633923,
+              0.0457091,
+              -0.022143621,
+              -0.0007423012,
+              -0.03613117,
+              0.052107,
+              0.02962152,
+              0.045084383,
+              0.044733327,
+              0.11753868,
+              0.05730107,
+              0.026509244,
+              -0.056454167,
+              -0.017637681,
+              0.030301955,
+              0.04790331,
+              -0.025398305,
+              -0.019705286,
+              0.11366949,
+              0.05800383,
+              -0.0072742635,
+              0.100181706,
+              0.1609472,
+              0.0053162435,
+              0.01714287,
+              -0.023215268,
+              0.042824704,
+              0.04082185,
+              0.030668061,
+              -0.06529372,
+              0.008288249,
+              0.0325246,
+              0.009664108,
+              -0.031153189,
+              0.044064675,
+              0.10059426,
+              0.036557477,
+              0.009674479,
+              0.016028037,
+              0.02236809,
+              0.056538712,
+              -0.12828006,
+              0.016760435,
+              0.015355689,
+              -0.00070172164,
+              -0.0076741586,
+              -0.02880062,
+              -0.011680436,
+              -0.036522433,
+              -0.030315956,
+              0.023295958,
+              0.031333964,
+              0.042397793,
+              -0.063102156,
+              0.0669075,
+              -0.07678097,
+              0.0616129,
+              -0.0071245604,
+              -0.021313114,
+              0.0040440215,
+              0.04436404,
+              0.05289292,
+              0.05803014,
+              0.032691576,
+              0.037537806,
+              -0.09712317,
+              -0.0061692744,
+              0.008186577,
+              -0.0151672475,
+              -0.05499382,
+              -0.11011894,
+              -0.017255861,
+              0.061501417,
+              0.03551128,
+              0.056205165,
+              0.07500363,
+              0.023062926,
+              0.10787879,
+              0.063290246,
+              -0.021196125,
+              -0.005724647,
+              0.019805718,
+              -0.0063712946,
+              -0.049270064,
+              -0.024442751,
+              0.018587058,
+              -0.082689136,
+              -0.019034613,
+              0.005483609,
+              0.03418548,
+              -0.008317338,
+              0.06888298,
+              -0.037655607,
+              -0.05362105,
+              -0.010807861,
+              0.069666155,
+              -0.01777964,
+              -0.015136251,
+              -0.026567455,
+              -0.08084807,
+              -0.078372054,
+              0.039493512,
+              0.013156698,
+              0.07340631,
+              0.12035369,
+              -0.05765069,
+              0.025966862,
+              -0.0045753582,
+              -0.030865112,
+              0.039448086,
+              -0.037273232,
+              0.047059145,
+              -0.029127738,
+              -0.024217308,
+              0.02748501,
+              -0.048555836,
+              0.017913114,
+              -0.055981673,
+              -0.005601368,
+              -0.04045025,
+              -0.017308103,
+              0.06272273,
+              0.012256746,
+              0.01575095,
+              -0.026737463,
+              0.04115108,
+              0.07562276,
+              -0.01140116,
+              0.022552952,
+              0.0443809,
+              -0.030472409,
+              -0.021670958,
+              -0.037897367,
+              0.017250286,
+              -0.033001736,
+              -0.048738975,
+              -0.06429833,
+              -0.015412785,
+              0.0036735258,
+              0.023700202,
+              0.035861194,
+              -0.05393875,
+              0.048050668,
+              0.032297045,
+              0.021352977,
+              -0.05701748,
+              0.0008330949,
+              -0.006661303,
+              -0.0070953164,
+              -0.043984424,
+              0.052504774,
+              0.027689766,
+              0.031661708,
+              -0.050054867,
+              -0.015419155,
+              -0.013700429,
+              -0.03579233,
+              -0.08926211,
+              -0.034341693,
+              -0.01738188,
+              -0.0065487004,
+              -0.051955026,
+              0.0019674778,
+              0.0015172043,
+              0.024915336,
+              0.010987228,
+              0.061529815,
+              0.09077649,
+              0.04394813,
+              -0.07503514,
+              0.043345768,
+              -0.028357483,
+              0.06312762,
+              0.025069924,
+              0.028561853,
+              0.043048594,
+              0.017411513,
+              -0.025240859,
+              -0.0056393985,
+              0.054039005,
+              0.008721963,
+              -0.039967448,
+              0.0012871448,
+              0.0052062417,
+              0.005563228,
+              0.042596456,
+              -0.008794862,
+              -0.044669237,
+              0.04184779,
+              0.008726271,
+              0.10136058,
+              0.040724736,
+              0.14168875,
+              -0.017516509,
+              -0.11203568,
+              0.0010548063,
+              -0.058536656,
+              0.01673066,
+              0.007502946,
+              -0.035662595,
+              0.034719367,
+              -0.0060368567,
+              0.13295838,
+              0.026423598,
+              0.056147255,
+              0.04473965,
+              0.045232397,
+              0.07171366,
+              0.009358642,
+              -0.021109166,
+              0.033915937,
+              0.0380073,
+              -0.01451498,
+              -0.021589639,
+              0.062518574,
+              -0.017531183,
+              -0.030811403,
+              0.024500312,
+              0.05383414,
+              -0.1335839,
+              0.01834579,
+              -0.051048376,
+              0.07460228,
+              0.03231806,
+              0.00962887,
+              0.05156732,
+              0.016169788,
+              0.0062234807,
+              -0.09062714,
+              -0.08959952,
+              0.025153147,
+              -0.030351512,
+              -0.04339584,
+              0.007234872,
+              0.014588551,
+              0.022614833,
+              -0.08844599,
+              -0.009002514,
+              -0.114522785,
+              0.08118862,
+              -0.03023919,
+              0.007820294,
+              0.043863248,
+              -0.043678157,
+              -0.036323708,
+              0.006777855,
+              -0.019326974,
+              -0.0664114,
+              -0.019019991,
+              0.073445216,
+              -0.039277073,
+              -0.0157583,
+              -0.01931436,
+              -0.027121417,
+              -0.028259363,
+              -0.107222356,
+              0.11150329,
+              -0.012612926,
+              -0.025338905,
+              0.029330198,
+              0.011753977,
+              0.009784897,
+              0.042475123,
+              -0.004051051,
+              -0.014803267,
+              -0.04530689,
+              -0.01848677,
+              -0.050840423,
+              0.01814009,
+              0.0051442874,
+              -0.033988528,
+              0.0033705293,
+              -0.05515113,
+              -0.023601055,
+              -0.06183089,
+              0.012501645,
+              -0.08027637,
+              0.022573682,
+              0.079796925,
+              -0.00926268,
+              -0.02180816,
+              0.0059841494,
+              -0.018863965,
+              -0.011257763,
+              0.055679787,
+              -0.018714463,
+              -0.04081558,
+              -0.017017504,
+              0.026006198,
+              -0.03687599,
+              -0.05399378,
+              0.042955294,
+              0.00079697353,
+              -0.0015601065,
+              0.026138263,
+              -0.01198548,
+              0.07594801,
+              -0.0049053924,
+              -0.001241132,
+              0.022863775,
+              0.025632044,
+              -0.023908222,
+              -0.02252925,
+              0.042020634,
+              -0.060588334,
+              0.05498828,
+              -0.03466166,
+              0.003202133,
+              -0.015508297,
+              -0.021138275,
+              0.007791096,
+              0.052594397,
+              -0.08649948,
+              0.038542755,
+              0.011088168,
+              0.049710445,
+              -0.015898548,
+              0.013559725,
+              -0.0012927915,
+              -0.078937665,
+              -0.0470789,
+              0.02421941,
+              0.0050838543,
+              -0.051634457,
+              0.014016644,
+              0.059073824,
+              -0.01279741,
+              0.006315097,
+              0.028651753,
+              -0.023221422,
+              -0.049021006,
+              -0.08123552,
+              -0.027243393,
+              -0.026543872,
+              0.040068373,
+              0.01465917,
+              0.01366034,
+              -0.07191417,
+              -0.007906117,
+              -0.06743931,
+              -0.040284913,
+              0.046346053,
+              -0.015108051,
+              -0.067285545,
+              0.020757562,
+              -0.03144588,
+              -0.02684228,
+              -0.030008601,
+              0.0008360872,
+              -0.012667347,
+              -0.0782403,
+              0.02436115,
+              -0.054881096,
+              -0.010856299,
+              -0.07653927,
+              -0.044655506,
+              -0.02075821,
+              0.023765713,
+              0.0083463555,
+              0.026002545,
+              -0.003060633,
+              0.060491852,
+              0.032562606,
+              0.029937308,
+              -0.022013078,
+              0.07388013,
+              0.017152807,
+              -0.07095613,
+              -0.03923808,
+              0.0017680842,
+              0.0038672008,
+              -0.053012144,
+              -0.016951663,
+              0.027642388,
+              0.016483316,
+              -0.015618807,
+              -0.11136081,
+              0.006826955,
+              -0.010586094,
+              -0.05052998,
+              -0.04226535,
+              -0.031801827,
+              -0.020531418,
+              -0.06278464,
+              -0.062224947,
+              0.0769673,
+              -0.0706861,
+              0.026174366,
+              -0.041260213,
+              0.058052614,
+              -0.046227556,
+              -0.05443509,
+              0.007650712,
+              -0.061986744,
+              -0.00546975,
+              -0.042977307,
+              -0.0147894155,
+              0.045748055,
+              -0.01602859,
+              0.018538997,
+              0.073324144,
+              -0.105757244,
+              -0.010215157,
+              0.0069961487,
+              -0.010474333,
+              0.007267861,
+              -0.043416463,
+              0.04171331,
+              0.012246647,
+              -0.024870023,
+              0.0067938967,
+              0.023995718,
+              0.037606664,
+              -0.034879085,
+              0.107255146,
+              0.019311333,
+              0.008084773,
+              0.015113109,
+              0.04807634,
+              -0.011898967,
+              0.0028230203,
+              0.004201883,
+              -0.019952193,
+              -0.083809994,
+              0.025964422,
+              0.010652608,
+              0.021981532,
+              -0.029947964,
+              0.10096241,
+              -0.0018155909,
+              -0.078443065,
+              0.035357803,
+              0.030101022,
+              0.08652985,
+              -0.020698488,
+              0.06619985,
+              0.011043828,
+              0.022531942,
+              0.059432585,
+              -0.08669654,
+              0.023926888,
+              0.006353244,
+              -0.046637908,
+              -0.072916985,
+              -0.04355625,
+              -0.010734682,
+              -0.06298886,
+              0.11202974,
+              -0.008399903,
+              0.04045217,
+              -0.049840588,
+              -0.051897135,
+              0.04921834,
+              0.018730633,
+              0.07189677,
+              -0.020521715,
+              0.10433443,
+              -0.0035553537,
+              0.015335822,
+              -0.03326729,
+              -0.05246277,
+              -0.038786076,
+              0.04000599,
+              -0.028919725,
+              -0.017996594,
+              -0.007428113,
+              -0.003258321,
+              0.0127034895,
+              -0.0062633064,
+              0.0007574967,
+              -0.060385525,
+              -0.018971093,
+              0.062526286,
+              -0.025764955,
+              0.05286283,
+              0.043842334,
+              0.044092383,
+              -0.037126385,
+              -0.018775577,
+              0.007996275,
+              -0.00028039515,
+              -0.06591952,
+              0.039109394,
+              0.022268493,
+              0.033030964,
+              0.010780152,
+              0.051087722,
+              -0.07398754,
+              0.02156791,
+              -0.03391487,
+              0.01900175,
+              -0.03438655,
+              -0.050286565,
+              -0.029407075,
+              0.013486627,
+              0.006069821,
+              0.03566702,
+              -0.046612754,
+              0.030740444,
+              -0.0637836,
+              0.020758858,
+              0.013579259,
+              0.015677635,
+              0.07067559,
+              -0.03354964,
+              -0.09833861,
+              -0.045598283,
+              0.046094477,
+              -0.018735003,
+              0.0013117951,
+              0.020225674,
+              -0.025771514,
+              -0.011772435,
+              0.020403381,
+              0.048393097,
+              -0.001137191,
+              -0.008214463,
+              -0.024194324,
+              0.012559411,
+              0.028170707,
+              -0.038262583,
+              -0.010594243,
+              0.008866333,
+              0.02652175,
+              0.010765866,
+              0.02152175,
+              0.007194773,
+              -0.021046689,
+              -0.047594506,
+              -0.05342931,
+              0.044459403,
+              -0.00075621146,
+              0.021768885,
+              0.061362576,
+              0.03243972,
+              0.023200674,
+              0.012056035,
+              -0.010374278,
+              -0.06796502,
+              -0.0056832493,
+              0.048799623,
+              -0.035878677,
+              -0.020508701,
+              0.03527651,
+              0.096402384,
+              -0.027735645,
+              0.11728837,
+              0.022490505,
+              -0.08394513,
+              -0.010033967,
+              0.024851669,
+              -0.019062884,
+              0.00039440763,
+              -0.10133529,
+              0.011722217,
+              -0.04434193,
+              -0.030069547,
+              0.030103652,
+              -0.017366616,
+              0.046203658,
+              -0.04393208,
+              -0.05095759,
+              -0.04554081,
+              -0.029142734,
+              0.01689045,
+              0.008356038,
+              -0.035321265,
+              -0.02382173,
+              -0.0015672153,
+              0.06304823,
+              -0.008137697,
+              -0.014463008,
+              0.045292154,
+              -0.06497864,
+              0.015265712,
+              0.008239593,
+              -0.08195689,
+              0.037012544,
+              0.04680898,
+              0.007484248,
+              0.02335733,
+              -0.06787198,
+              -0.062197443,
+              -0.06841327,
+              -0.039720036,
+              -0.0105394935,
+              -0.057220835,
+              -0.039479975,
+              0.029730098,
+              0.0697698,
+              0.0280752,
+              0.0137115335,
+              -0.0045632124,
+              -0.01313052,
+              0.07553262,
+              -0.04117193,
+              -0.14872926,
+              0.028015105,
+              -0.047134113,
+              -0.016151398,
+              -0.081647106,
+              -0.02221662,
+              -0.036281105,
+              -0.023036504,
+              0.0612415,
+              -0.018361837,
+              -0.0238258,
+              -0.0022532772,
+              0.1537845,
+              0.006872191,
+              -0.044352733,
+              -0.0026320857,
+              -0.08600976,
+              0.005572628,
+              0.053448226,
+              -0.015072955,
+              -0.029777542,
+              -0.019132927,
+              0.053970527,
+              0.005238485,
+              -0.02418231,
+              -0.12369688,
+              0.0014781327,
+              0.059662092,
+              -0.011181213,
+              0.01400666,
+              0.023866476,
+              -0.059490796,
+              -0.054530527,
+              -0.011234197,
+              0.013823349,
+              -0.012150345,
+              -0.09948839,
+              0.023659766,
+              0.014326883,
+              -0.02229736,
+              -0.0024076505,
+              -0.10091382,
+              0.08174192,
+              -0.024408998,
+              -0.023222951,
+              0.011201234,
+              0.013236311,
+              0.04317295,
+              0.051764306,
+              0.07648576,
+              -0.00061111146,
+              -0.088623054,
+              -0.037177067,
+              0.038964123,
+              -0.029959839,
+              0.033466227,
+              -0.08635276,
+              0.04128183,
+              -0.020397836,
+              0.056285754,
+              -0.02570748,
+              0.05911732,
+              0.0061064134,
+              -0.01733281,
+              -0.0875996,
+              -0.0127257295,
+              -0.013593507,
+              -0.04925175,
+              0.01888016,
+              -0.032455195,
+              -0.023753202,
+              0.052025676,
+              0.06000905,
+              0.04137704,
+              0.004952635,
+              -0.02542677,
+              0.00017748028,
+              -0.041987997,
+              0.04760188,
+              0.068178274,
+              -0.060950078,
+              -0.05742421,
+              0.054274186,
+              -0.048096504,
+              0.034568857,
+              0.0012921172,
+              0.0705816,
+              -0.014679933,
+              -0.001761971,
+              -0.029119784,
+              0.008006632,
+              0.018063113,
+              -0.05880496,
+              -0.052486468,
+              0.010976936,
+              0.03688557,
+              0.061141517,
+              -0.009467033,
+              -0.035062946,
+              -0.06794524,
+              -0.0609979,
+              0.015924038,
+              -0.03805085,
+              0.03977454,
+              -0.015656536,
+              0.014254484,
+              -0.030620195,
+              -0.038830906,
+              -0.013730216,
+              -0.070247106,
+              -0.074514836,
+              0.037831023,
+              0.027780455,
+              0.0073002693,
+              -0.050368425,
+              0.040389538,
+              0.035920046,
+              0.025425838,
+              0.006255748,
+              -0.017454483,
+              -0.02307413,
+              0.05788845,
+              0.018672187,
+              0.033335716,
+              0.01855402,
+              0.07957198,
+              -0.0029801806,
+              -0.057038378,
+              0.010123766,
+              0.038190138,
+              0.0333764,
+              0.075057626,
+              0.00592374,
+              0.06380629,
+              -0.028154025,
+              0.07188246,
+              -0.056649268,
+              -0.019166004,
+              0.053392358,
+              0.13961181,
+              -0.08459373,
+              0.03255955
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "togethercomputer/m2-bert-80M-32k-retrieval",
+        "object": "list",
+        "usage": null
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/0b27fd737699.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:13:57.556416Z",
+        "created_at": "2025-09-03T17:37:47.461886Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 432363250,
-        "load_duration": 159296417,
+        "total_duration": 338927833,
+        "load_duration": 100895125,
         "prompt_eval_count": 223,
-        "prompt_eval_duration": 257000000,
+        "prompt_eval_duration": 221583042,
         "eval_count": 2,
-        "eval_duration": 14000000,
+        "eval_duration": 12341416,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/0b3f2e4754ff.json

@@ -24,7 +24,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -39,7 +39,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921333,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -50,7 +50,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -65,7 +65,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921333,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -76,7 +76,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -91,7 +91,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921333,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -102,7 +102,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -117,7 +117,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921333,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -128,7 +128,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -143,7 +143,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921334,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -154,7 +154,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -169,7 +169,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921334,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -180,7 +180,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -195,7 +195,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921334,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -206,7 +206,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-29",
+          "id": "chatcmpl-414",
           "choices": [
             {
               "delta": {
@@ -221,7 +221,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090031,
+          "created": 1756921334,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,

tests/integration/recordings/responses/0c1f45455d3b.json

@@ -0,0 +1,59 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello, world!"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "oBUtgGr-4Yz4kd-9801a2f00b2b42e8",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "Hello! It's nice to meet you. Is there something I can help you with or would you like to chat?",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": []
+            },
+            "seed": 1098425109146507500
+          }
+        ],
+        "created": 1758039052,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 25,
+          "prompt_tokens": 39,
+          "total_tokens": 64,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/0e8f2b001dd9.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -20,14 +20,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-368",
+        "id": "chatcmpl-161",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "Saturn is known for its extensive ring system.",
+              "content": "The answer is Saturn.",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -37,15 +37,15 @@
             }
           }
         ],
-        "created": 1754081853,
+        "created": 1756921364,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 11,
+          "completion_tokens": 6,
           "prompt_tokens": 39,
-          "total_tokens": 50,
+          "total_tokens": 45,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }

tests/integration/recordings/responses/0fda25b9241c.json

@@ -0,0 +1,71 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://shan-mfbb618r-eastus2.cognitiveservices.azure.com/openai/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-5-mini",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Which planet do humans live on?"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-5-mini"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "chatcmpl-CECIXqfvjuluKkZtG3q2QJoSQhBU0",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "Humans live on Earth \u2014 the third planet from the Sun. It's the only known planet that naturally supports life, with a breathable atmosphere, liquid water, and temperatures suitable for living organisms.",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": [],
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            },
+            "content_filter_results": {}
+          }
+        ],
+        "created": 1757499901,
+        "model": "gpt-5-mini-2025-08-07",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 112,
+          "prompt_tokens": 13,
+          "total_tokens": 125,
+          "completion_tokens_details": {
+            "accepted_prediction_tokens": 0,
+            "audio_tokens": 0,
+            "reasoning_tokens": 64,
+            "rejected_prediction_tokens": 0
+          },
+          "prompt_tokens_details": {
+            "audio_tokens": 0,
+            "cached_tokens": 0
+          }
+        },
+        "prompt_filter_results": [
+          {
+            "prompt_index": 0,
+            "content_filter_results": {}
+          }
+        ]
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/10eea8c15ddc.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:51.682357Z",
+        "created_at": "2025-09-03T17:37:33.473237Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 238161000,
-        "load_duration": 72494750,
+        "total_duration": 279025042,
+        "load_duration": 162673250,
         "prompt_eval_count": 212,
-        "prompt_eval_duration": 87000000,
+        "prompt_eval_duration": 73595834,
         "eval_count": 5,
-        "eval_duration": 74000000,
+        "eval_duration": 41950291,
         "response": "unsafe\nS8",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/140187e305dc.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -20,14 +20,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-876",
+        "id": "chatcmpl-974",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I'm afraid I don't have a built-in ability to directly interface with or \"test\" OpenAI models, including the original GPT-1 model. However, I can explain how you might approach this task:\n\nThe OpenAI GPT-1 is a large transformer-based language model that was trained on a massive dataset of text and achieved state-of-the-art results in various natural language processing tasks.\n\nTo test or evaluate the performance of a model like GPT-1, you would typically follow these steps:\n\n1. **Get access to the OpenAI API**: The OpenAI API provides a way for developers to interact with the GPT-1 model programmatically. You can sign up for an API key on the OpenAI website.\n2. **Choose a testing platform or environment**: You'll need a compute platform that supports the necessary algorithms and data structures to run inference on the GPT-1 model. Some popular options include AWS, Google Cloud, or Azure Compute Virtual Machines.\n3. **Prepare your test input data**: This will involve creating text inputs in the format expected by the OpenAI API (i.e., a JSON object containing the text to be processed).\n4. **Use the OpenAI Python library or SDK**: The OpenAI Python library provides an easy-to-use interface for interacting with the GPT-1 model through the API.\n\nHere's some example code that demonstrates how you might use the OpenAI Flask API to test a single input:\n\n```python\nfrom flask import Flask, request, jsonify\nimport json\n\napp = Flask(__name__)\n\n@ app . route ( '/ /gpt-en ', ' Text ', methods = ['POST'])\ndef gpt_en () -> Json :\n    data = request . get_json ()\n    if not data or \"message\" in ( data ):\n        return None , 400 , { ' error' : \"Input must be a text string.\" }\n    response = []\n    while True:\n        message = \"\"\n        for token in data [\"input\"]:\n            response_text = f\"{data['prompt']} {token}\"\n            data[\"input\"] = [response_text]\n            new_response = gpt_en()(data)\n            if all([not item or not isinstance(item, dict) for item in new_response]):\n             break\n\n        message = json . dumps ({}\"text\": response_text})\n        response.append(message)\n\n    return jsonify ({\"output\": response}), 200 , {}\n\nif __name__ == \"__main__\":\n   app.run(debug=True)\n```\n\n5. **Evaluate the output**: Once you have processed your test input data using the GPT-1 model, you can evaluate the accuracy of the generated responses.\n\nKeep in mind that this is just a basic example to illustrate how you might approach testing the OpenAI GPT-1 model.",
+              "content": "I'm happy to help you test the OpenAI API, however I can not access the API.\n\nInstead why don't we follow these steps:\n\n*   Check documentation\n*   Contact support\n*   Reach out to their community forum. \n\nLet me know if I can be of any additional assistance",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -37,15 +37,15 @@
             }
           }
         ],
-        "created": 1754510050,
+        "created": 1756921202,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 567,
+          "completion_tokens": 61,
           "prompt_tokens": 31,
-          "total_tokens": 598,
+          "total_tokens": 92,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }

tests/integration/recordings/responses/17030e75309f.json

@@ -0,0 +1,800 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "togethercomputer/m2-bert-80M-32k-retrieval",
+      "input": "This is completely different content"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "togethercomputer/m2-bert-80M-32k-retrieval"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              0.020581583,
+              0.03996682,
+              0.06342483,
+              -0.046694994,
+              -0.07684763,
+              -0.05265455,
+              -0.053058416,
+              -0.008007386,
+              -0.04512141,
+              0.03718547,
+              -0.026790882,
+              0.039592147,
+              0.08868821,
+              -0.054975007,
+              0.022950895,
+              -0.03249339,
+              0.05376096,
+              0.04878751,
+              0.06144113,
+              0.08925032,
+              -0.06345507,
+              -0.0008829904,
+              0.07914291,
+              -0.028592229,
+              -0.048433058,
+              -0.0351529,
+              0.028880889,
+              -0.08001268,
+              -0.04552556,
+              -0.080687605,
+              0.1400234,
+              0.14326853,
+              0.02891313,
+              -0.05588759,
+              0.007262874,
+              0.026984219,
+              0.09121335,
+              0.050748702,
+              0.017702162,
+              -0.035733465,
+              0.1328057,
+              -0.08973662,
+              -0.050988093,
+              -0.009071953,
+              0.00674055,
+              0.0138731655,
+              -0.024637444,
+              -0.0019375099,
+              0.019351467,
+              0.041681487,
+              0.09368255,
+              0.0052818935,
+              0.027539922,
+              -0.031472813,
+              0.042352878,
+              0.07326235,
+              0.010973438,
+              0.06776053,
+              0.06473745,
+              0.031266563,
+              0.00057834754,
+              -0.002110916,
+              0.16004054,
+              -0.0535361,
+              0.04453045,
+              0.050499436,
+              0.03501775,
+              -0.003733677,
+              0.020598825,
+              -0.079224035,
+              0.07070447,
+              -0.060201976,
+              0.006393084,
+              -0.003781692,
+              0.070510566,
+              -0.047214407,
+              0.06080987,
+              -0.0877733,
+              -0.08569845,
+              -0.018021964,
+              0.06378409,
+              0.027565937,
+              0.038700324,
+              -0.1248613,
+              0.00903349,
+              -0.08429076,
+              0.016536232,
+              0.025240825,
+              0.00043874417,
+              -0.004602262,
+              0.0457946,
+              -0.03598806,
+              0.056914188,
+              0.044693712,
+              0.011178773,
+              -0.020428436,
+              0.036093723,
+              0.031189999,
+              0.07220326,
+              -0.066868156,
+              -0.020061923,
+              -0.0563857,
+              -0.013928966,
+              -0.034524415,
+              0.0041604545,
+              -0.047119446,
+              0.033624567,
+              0.06970587,
+              -0.033320673,
+              -0.0413748,
+              0.01094969,
+              -0.0100499755,
+              0.004480598,
+              0.02067311,
+              -0.021157527,
+              0.022485765,
+              0.03633523,
+              0.0049809627,
+              0.02181411,
+              0.049156368,
+              0.06253565,
+              0.059981186,
+              -0.031591866,
+              -0.049331754,
+              0.033537455,
+              0.021542493,
+              0.009435254,
+              0.025516914,
+              0.025417773,
+              -0.07066102,
+              0.011794456,
+              0.06311989,
+              0.011093616,
+              0.08549021,
+              -0.04281618,
+              0.011115061,
+              0.07443118,
+              0.021961706,
+              -0.02724888,
+              -0.00047235374,
+              0.016601468,
+              0.043411057,
+              0.03835865,
+              0.01029931,
+              0.008437206,
+              -0.057274926,
+              -0.045377273,
+              -0.09733081,
+              -0.009755395,
+              0.028172465,
+              0.043972567,
+              0.0968819,
+              0.052496422,
+              0.031553026,
+              -0.019291716,
+              0.034150966,
+              0.1310106,
+              0.02864821,
+              -0.047452684,
+              0.016342362,
+              -0.06591784,
+              -0.064888336,
+              -0.03380424,
+              -0.08384223,
+              0.023302404,
+              -0.020427782,
+              0.019540966,
+              0.02240307,
+              0.026848866,
+              -0.0018868797,
+              -0.031800512,
+              -0.073483676,
+              0.08840526,
+              -0.02696041,
+              -0.042041607,
+              0.030633071,
+              0.020918656,
+              0.06119309,
+              -0.048348967,
+              0.036555305,
+              0.033583682,
+              0.019630525,
+              -0.03500669,
+              -0.020821452,
+              0.012256841,
+              0.06733756,
+              0.036884613,
+              -0.080063485,
+              0.019956889,
+              -0.01994667,
+              0.0011630546,
+              -0.08307688,
+              -0.040326167,
+              -0.03293244,
+              -0.014897417,
+              0.03977495,
+              0.036790676,
+              0.020645684,
+              0.015943283,
+              -0.05961047,
+              0.036905374,
+              0.006005009,
+              0.033375766,
+              -0.015491932,
+              -0.07008363,
+              -0.031575754,
+              -0.0065630106,
+              -0.013962699,
+              -0.012629252,
+              0.046026245,
+              0.007901817,
+              -0.117550366,
+              -0.06314231,
+              0.05348636,
+              0.10863247,
+              0.053361807,
+              0.055756297,
+              -0.026388792,
+              -0.011777907,
+              -0.07197253,
+              0.010918023,
+              0.020021347,
+              0.14850953,
+              -0.043404948,
+              -0.04262303,
+              -0.04904758,
+              -0.014644666,
+              -0.0018742547,
+              -0.0054880613,
+              -0.015058903,
+              -0.03137978,
+              -0.09884002,
+              0.048087206,
+              -0.00044948232,
+              -0.059237186,
+              0.01681299,
+              0.06357592,
+              0.09665662,
+              -0.032431144,
+              -0.021346267,
+              -0.03630939,
+              0.108024776,
+              0.011421504,
+              0.00090062595,
+              0.09738569,
+              0.07588425,
+              -0.038476508,
+              0.008637763,
+              0.03942589,
+              0.03673421,
+              -0.008536316,
+              -0.035427485,
+              -0.0571462,
+              0.077514425,
+              -0.014574157,
+              -0.06636753,
+              0.0356625,
+              0.00055575924,
+              -0.008948914,
+              0.00082343427,
+              0.0511982,
+              0.03143358,
+              -0.03388075,
+              -0.013724427,
+              0.0551338,
+              -0.007191376,
+              -0.05363105,
+              -0.07718383,
+              -0.008230843,
+              0.10335533,
+              0.013668598,
+              -0.08284561,
+              0.05179483,
+              -0.08437943,
+              -0.017510848,
+              -0.05778264,
+              0.044004828,
+              -0.02612715,
+              -0.0058190715,
+              0.013293448,
+              -0.005663543,
+              0.0037016177,
+              -0.020699238,
+              0.00277368,
+              0.041328322,
+              -0.052624915,
+              0.020320976,
+              0.0033441507,
+              -0.11465616,
+              -0.059619453,
+              -0.029252917,
+              0.014145012,
+              -0.049234822,
+              0.025969574,
+              0.04118447,
+              0.017938918,
+              -0.009885965,
+              0.012801603,
+              -0.0007332413,
+              -0.0012993023,
+              -0.052635074,
+              0.064850755,
+              0.004576457,
+              -0.018446025,
+              -0.069130346,
+              0.018532049,
+              0.006330208,
+              0.039377607,
+              0.11237417,
+              0.055357743,
+              -0.0038629018,
+              0.048188694,
+              0.052925084,
+              -0.011272187,
+              -0.012422014,
+              0.005874242,
+              -0.0007749841,
+              -0.058404274,
+              -0.022589723,
+              0.031956926,
+              0.0470711,
+              0.027993023,
+              -0.06112344,
+              -0.0119517995,
+              -0.09797626,
+              -0.073644884,
+              0.07465703,
+              0.09884925,
+              -0.035564825,
+              -0.040369682,
+              0.014445328,
+              -0.052219898,
+              -0.027498178,
+              0.036846854,
+              -0.09408649,
+              -0.00027856976,
+              0.028489627,
+              0.002446708,
+              -0.043065134,
+              -0.030562297,
+              0.07565528,
+              -0.0256914,
+              -0.12143018,
+              0.09360902,
+              0.015026368,
+              0.058814585,
+              -0.01885037,
+              0.04901136,
+              0.009521308,
+              -0.0067844316,
+              -0.06265128,
+              0.029733902,
+              0.019703392,
+              -0.029863501,
+              0.033668272,
+              -0.015967827,
+              -0.024716265,
+              0.07095029,
+              0.07264489,
+              -0.021480447,
+              -0.040650267,
+              -0.11752601,
+              0.019378915,
+              -0.042310815,
+              0.05690114,
+              -0.01413233,
+              0.058113046,
+              -0.073345415,
+              -0.059576523,
+              -0.09720947,
+              0.012149926,
+              0.057291746,
+              -0.03505685,
+              -0.038375836,
+              0.0149342865,
+              -0.001562935,
+              -0.023513826,
+              0.00014910847,
+              0.022598296,
+              -0.071317434,
+              -0.06260575,
+              4.0522777e-05,
+              -0.086758316,
+              -0.013101295,
+              -0.02990748,
+              -0.08461068,
+              0.016139807,
+              0.06101953,
+              -0.08451055,
+              -0.046145856,
+              -0.048467644,
+              0.060105037,
+              0.024200678,
+              0.052542347,
+              0.041119967,
+              -0.0068898834,
+              0.09487794,
+              0.012641435,
+              -0.13026047,
+              0.06284531,
+              0.018659385,
+              -0.07564698,
+              0.006965884,
+              -0.036618453,
+              0.118192144,
+              -0.04771263,
+              0.023280941,
+              0.054039616,
+              -0.114724584,
+              -0.0918062,
+              0.038803104,
+              -0.09954885,
+              0.008216844,
+              -0.030975524,
+              -0.030176945,
+              0.0397766,
+              -0.0061745024,
+              0.071971394,
+              -0.041089423,
+              0.033857126,
+              0.03961017,
+              -0.03826589,
+              0.038435444,
+              -0.0860421,
+              0.08869605,
+              -0.028628873,
+              -0.05565758,
+              0.056920726,
+              0.020458337,
+              0.05994542,
+              0.08241441,
+              0.0400861,
+              -0.0045191804,
+              0.0030094406,
+              -0.007466077,
+              -0.02953672,
+              -0.068642505,
+              0.060889505,
+              -0.029501854,
+              -0.048823155,
+              0.015409609,
+              0.018862283,
+              -0.016425489,
+              -0.087497436,
+              0.067643866,
+              -0.033761434,
+              -0.054749027,
+              -0.03657711,
+              0.038102675,
+              -0.06197178,
+              0.045409728,
+              -0.02127562,
+              0.064449035,
+              -0.0056471447,
+              0.067553245,
+              -0.07137091,
+              0.017407946,
+              -0.09813906,
+              -0.046500444,
+              -0.058283363,
+              -0.018302118,
+              -0.025382183,
+              -0.04259567,
+              0.022398086,
+              -0.09098867,
+              0.043438766,
+              -0.07656342,
+              0.0028111413,
+              0.030880956,
+              -0.07750997,
+              0.07084878,
+              0.05344556,
+              0.0052658613,
+              -0.025303314,
+              -0.04759683,
+              -0.017034022,
+              0.02855913,
+              -0.04999449,
+              0.01974624,
+              0.07708244,
+              -0.011766297,
+              0.057390995,
+              -0.04652422,
+              0.023833811,
+              0.05608237,
+              0.05765577,
+              0.05078112,
+              0.046039928,
+              -0.055372067,
+              -0.044933185,
+              -0.08522771,
+              -0.09142792,
+              0.012817157,
+              -0.026148932,
+              -0.07331254,
+              0.11312438,
+              0.055893615,
+              -0.013500698,
+              0.008603385,
+              0.00057156937,
+              -0.091709465,
+              0.08057745,
+              -0.011340835,
+              -0.016915537,
+              0.0011427286,
+              0.09740327,
+              -0.029696029,
+              -0.047760956,
+              0.015541391,
+              0.0955123,
+              0.021890407,
+              -0.02908531,
+              0.030994056,
+              0.03820344,
+              -0.062488347,
+              0.015730608,
+              0.021182666,
+              -0.043783836,
+              0.02782434,
+              0.11151618,
+              0.052450567,
+              0.00037089732,
+              0.03351987,
+              -0.0054050605,
+              -0.033424556,
+              0.10350312,
+              0.065157756,
+              0.03392563,
+              0.010131469,
+              -0.053846426,
+              -0.0022781377,
+              0.0014610494,
+              0.005763698,
+              0.0426489,
+              -0.08206464,
+              -0.07099776,
+              -0.04228286,
+              0.07337842,
+              0.047744617,
+              0.04284143,
+              0.06959166,
+              0.013133698,
+              -0.030711556,
+              0.009055728,
+              0.06162162,
+              0.017240932,
+              -0.039795205,
+              -0.10877084,
+              0.024329182,
+              -0.0049141976,
+              -0.038892467,
+              -0.012901915,
+              -0.095080145,
+              0.05290344,
+              0.021141307,
+              0.03017632,
+              -0.0044154925,
+              -0.10163907,
+              -0.08186605,
+              -0.023801327,
+              0.035552323,
+              0.039041802,
+              -0.032427292,
+              0.07541,
+              0.10233232,
+              0.018622704,
+              -0.013646388,
+              -0.008619573,
+              0.020216271,
+              -0.07897946,
+              0.063637026,
+              -0.08652915,
+              -0.0100032855,
+              0.046902858,
+              0.076707095,
+              0.02531022,
+              0.05425257,
+              0.015954422,
+              -0.033368777,
+              -0.025112148,
+              -0.01394599,
+              -0.04062625,
+              0.056534503,
+              -0.04304168,
+              -0.060214523,
+              0.016551849,
+              -0.006314451,
+              0.060458317,
+              0.027808908,
+              0.040655438,
+              -0.031415448,
+              -0.120496035,
+              -0.04355332,
+              0.002170874,
+              0.013876282,
+              -0.011508199,
+              -0.046841078,
+              0.076444104,
+              0.08982719,
+              0.0846208,
+              0.029678846,
+              -0.086331986,
+              0.14421903,
+              -0.0030989156,
+              0.01598773,
+              0.059804816,
+              -0.0464971,
+              -0.0058899643,
+              0.02542227,
+              -0.020552263,
+              0.10621325,
+              -0.023809364,
+              -0.13324538,
+              -0.075492345,
+              0.06716611,
+              -0.040477127,
+              -0.046582364,
+              -0.07376809,
+              0.024235222,
+              0.070477486,
+              0.11006968,
+              -0.04869493,
+              0.078016356,
+              -0.07615679,
+              0.08063025,
+              -0.016255612,
+              -0.051746953,
+              0.08059405,
+              -0.0025989392,
+              -0.073428795,
+              -0.03987752,
+              0.098251894,
+              -0.006217126,
+              -0.028130062,
+              -0.051326722,
+              -0.0470711,
+              -0.016759045,
+              -0.039230157,
+              -0.020525763,
+              0.07148479,
+              -0.05419997,
+              -0.025775867,
+              0.0070432695,
+              -0.006410803,
+              0.027631486,
+              0.037966132,
+              -0.025654731,
+              -0.023324372,
+              0.026257442,
+              -0.034822363,
+              -0.010826962,
+              0.020623349,
+              0.0523646,
+              -0.022230538,
+              0.028196862,
+              0.023292363,
+              0.12025986,
+              -0.022648653,
+              -0.061013527,
+              -0.040045265,
+              0.022293845,
+              -0.016287014,
+              -0.08896512,
+              -0.021426601,
+              0.05109808,
+              0.038455352,
+              0.055882193,
+              0.10342665,
+              0.06503611,
+              0.07195616,
+              -0.013601524,
+              0.028618002,
+              0.03990776,
+              0.03236452,
+              0.07085622,
+              0.0055737793,
+              0.013130723,
+              -0.066394895,
+              0.021342268,
+              0.0026651763,
+              -0.012577644,
+              0.049445108,
+              0.049437333,
+              0.0047207237,
+              -0.02006381,
+              0.02022424,
+              0.05142978,
+              0.01725655,
+              0.00037797724,
+              0.039846063,
+              -0.11509461,
+              -0.013602717,
+              -0.066661686,
+              -0.020612884,
+              0.012832718,
+              -0.091352694,
+              -0.09389515,
+              0.07369748,
+              0.056452867,
+              0.10581744,
+              -0.06383743,
+              0.036662158,
+              -0.07204409,
+              0.012689036,
+              -0.025724197,
+              0.040817674,
+              -0.06890574,
+              0.0055584335,
+              0.031956017,
+              0.0014588524,
+              0.098465145,
+              0.0054196557,
+              0.056656968,
+              0.03322914,
+              -0.040962957,
+              -0.015689995,
+              -0.034545593,
+              -0.052660752,
+              -0.044768244,
+              -0.04419147,
+              -0.11039146,
+              0.015522225,
+              0.0052053384,
+              -0.08471112,
+              0.025280464,
+              -0.03353502,
+              -0.018717872,
+              -0.020738749,
+              0.0021664763,
+              -0.011238148,
+              0.02322494,
+              0.010894536,
+              -0.09676859,
+              0.01013113,
+              0.0035604087,
+              -0.0060942546,
+              -0.027839229,
+              -0.0037214137,
+              0.053193003,
+              -0.070640355,
+              -0.07783396,
+              0.005814805,
+              0.0064411093,
+              -0.023913933,
+              0.030543711,
+              -0.07979223,
+              -0.008982119,
+              0.043360766,
+              -0.048063844,
+              0.0017047173,
+              0.06882568,
+              -0.03443207,
+              0.015080402,
+              -0.049461022,
+              0.045471057,
+              -0.031460688,
+              -0.0028212033,
+              0.044725604,
+              0.0026248703,
+              -0.0329393,
+              -0.034404054,
+              0.024516258,
+              0.002614168,
+              -0.047855787,
+              -0.03149,
+              0.14646776,
+              -0.047660008,
+              0.021453902
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "togethercomputer/m2-bert-80M-32k-retrieval",
+        "object": "list",
+        "usage": null
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/17253d7cc667.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:52.919624Z",
+        "created_at": "2025-09-03T17:37:34.308033Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 201956834,
-        "load_duration": 105132584,
+        "total_duration": 200296000,
+        "load_duration": 115974708,
         "prompt_eval_count": 212,
-        "prompt_eval_duration": 75000000,
+        "prompt_eval_duration": 72173459,
         "eval_count": 2,
-        "eval_duration": 20000000,
+        "eval_duration": 11536750,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/173ecb3aab28.json

@@ -40,7 +40,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -55,7 +55,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -66,7 +66,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -81,7 +81,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -92,7 +92,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -107,7 +107,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -118,7 +118,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -133,7 +133,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -144,7 +144,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -159,7 +159,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -170,7 +170,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -185,7 +185,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -196,7 +196,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -211,7 +211,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -222,7 +222,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-457",
+          "id": "chatcmpl-921",
           "choices": [
             {
               "delta": {
@@ -237,7 +237,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754090032,
+          "created": 1756920971,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,

tests/integration/recordings/responses/174458ad71b2.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:53.580806Z",
+        "created_at": "2025-09-03T17:37:34.994704Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 205732750,
-        "load_duration": 98967000,
+        "total_duration": 339570875,
+        "load_duration": 262794125,
         "prompt_eval_count": 213,
-        "prompt_eval_duration": 86000000,
+        "prompt_eval_duration": 64061000,
         "eval_count": 2,
-        "eval_duration": 18000000,
+        "eval_duration": 11839042,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/178016edef0e.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:52.354566Z",
+        "created_at": "2025-09-03T17:37:33.769233Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 605192500,
-        "load_duration": 457087166,
+        "total_duration": 253836584,
+        "load_duration": 138624959,
         "prompt_eval_count": 210,
-        "prompt_eval_duration": 63000000,
+        "prompt_eval_duration": 69496125,
         "eval_count": 5,
-        "eval_duration": 84000000,
+        "eval_duration": 45062833,
         "response": "unsafe\nS12",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/197228e26971.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:52.686478Z",
+        "created_at": "2025-09-03T17:37:34.074233Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 304136208,
-        "load_duration": 155977000,
+        "total_duration": 270746375,
+        "load_duration": 156423042,
         "prompt_eval_count": 213,
-        "prompt_eval_duration": 71000000,
+        "prompt_eval_duration": 70338083,
         "eval_count": 5,
-        "eval_duration": 76000000,
+        "eval_duration": 43379167,
         "response": "unsafe\nS2",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/198ef7208389.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:51.186501Z",
+        "created_at": "2025-09-03T17:37:32.84197Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 3146184459,
-        "load_duration": 2533467917,
+        "total_duration": 21572898667,
+        "load_duration": 21155275042,
         "prompt_eval_count": 212,
-        "prompt_eval_duration": 526000000,
+        "prompt_eval_duration": 371898125,
         "eval_count": 5,
-        "eval_duration": 83000000,
+        "eval_duration": 43290458,
         "response": "unsafe\nS1",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/1adfaa0e062e.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:53.332041Z",
+        "created_at": "2025-09-03T17:37:34.607413Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 365895333,
-        "load_duration": 257825208,
+        "total_duration": 267812042,
+        "load_duration": 181570000,
         "prompt_eval_count": 213,
-        "prompt_eval_duration": 78000000,
+        "prompt_eval_duration": 73947375,
         "eval_count": 2,
-        "eval_duration": 28000000,
+        "eval_duration": 11708000,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/1b8394f90636.json

@@ -22,15 +22,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-08-04T22:55:05.685988Z",
+        "created_at": "2025-09-03T17:36:13.821929Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 14128980625,
-        "load_duration": 7220159208,
+        "total_duration": 1907912167,
+        "load_duration": 90979292,
         "prompt_eval_count": 18,
-        "prompt_eval_duration": 4658000000,
+        "prompt_eval_duration": 77350291,
         "eval_count": 43,
-        "eval_duration": 2224000000,
+        "eval_duration": 1738568334,
         "response": " _______.\n\nThe best answer is blue. The traditional nursery rhyme goes like this:\n\nRoses are red,\nViolets are blue,\nSugar is sweet,\nAnd so are you! (Or something similar.)",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/1b92be674e2a.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-07-31T17:50:06.140190726Z",
+        "created_at": "2025-09-03T17:39:38.236797Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 5213341378,
-        "load_duration": 43943569,
+        "total_duration": 1296281500,
+        "load_duration": 283393917,
         "prompt_eval_count": 23,
-        "prompt_eval_duration": 1049424427,
+        "prompt_eval_duration": 75453042,
         "eval_count": 24,
-        "eval_duration": 4119422888,
+        "eval_duration": 936860125,
         "response": "Mark Zuckerberg is the founder, chairman and CEO of Meta, which he originally founded as Facebook in 2004.",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/1e11c2b20ff8.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "How do systems learn automatically?"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              0.042460807,
+              -0.06189971,
+              -0.0784711,
+              0.0064329687,
+              0.03129365,
+              0.00807445,
+              0.05801836,
+              0.025447326,
+              0.016402787,
+              0.045995634,
+              -0.028924342,
+              0.04451832,
+              0.05686613,
+              -0.015340794,
+              -0.07020505,
+              -0.057178136,
+              -0.07683263,
+              0.006748679,
+              0.0043323045,
+              -0.123651944,
+              0.0031534543,
+              -0.03258051,
+              -0.02936216,
+              0.024140852,
+              -0.028559243,
+              0.10224467,
+              0.0021632623,
+              -0.006975691,
+              0.025292527,
+              -0.055500276,
+              0.031231727,
+              -0.0070274337,
+              0.08430815,
+              -0.028431177,
+              -0.083029,
+              0.009555893,
+              -0.020029299,
+              -0.00243229,
+              -0.00768719,
+              -0.023077851,
+              -0.09293533,
+              -0.042625993,
+              -0.020000124,
+              0.008240663,
+              0.060970567,
+              0.050315727,
+              -0.0510085,
+              -0.008543903,
+              -0.030227834,
+              -0.03582846,
+              -0.17836656,
+              -0.047279052,
+              0.033892106,
+              0.031623542,
+              -0.008832113,
+              0.10480918,
+              0.033559043,
+              0.090348184,
+              -0.015757555,
+              -0.0125672715,
+              -0.084686965,
+              -0.114781834,
+              -0.13755985,
+              0.021652374,
+              0.047834594,
+              0.043243896,
+              0.008659893,
+              0.038724966,
+              0.046716973,
+              -0.077413626,
+              -0.04887495,
+              0.031287406,
+              0.022356613,
+              0.00043283988,
+              0.052321073,
+              -0.012254071,
+              -0.035172574,
+              -0.00825216,
+              -0.008866574,
+              -0.034267236,
+              -0.04576201,
+              0.002467568,
+              -0.040877618,
+              0.08047682,
+              0.09472728,
+              0.0413438,
+              0.0057974122,
+              0.044982508,
+              0.025369909,
+              0.006618073,
+              0.010467276,
+              -0.07960384,
+              -0.03108485,
+              -0.03528749,
+              0.01831391,
+              0.053473305,
+              0.06568304,
+              -0.07259002,
+              0.02523736,
+              0.10520362,
+              0.035732146,
+              0.028157586,
+              0.011687256,
+              0.044207197,
+              0.012604437,
+              0.0018819098,
+              0.03926183,
+              0.043135095,
+              0.09784739,
+              -0.08801336,
+              -0.06060836,
+              0.02681984,
+              0.0041358666,
+              0.033492945,
+              0.011799116,
+              0.009551661,
+              -0.0095491735,
+              -0.021212189,
+              -0.008917248,
+              0.029352615,
+              -0.012693442,
+              -0.019269384,
+              0.009901157,
+              -0.00812101,
+              0.018603146,
+              -0.0007501193,
+              -0.056115113,
+              -3.8018077e-33,
+              0.020848714,
+              0.0047160466,
+              0.019726405,
+              0.06024251,
+              -0.0685974,
+              -0.07497267,
+              0.007997452,
+              -0.047339544,
+              0.057801835,
+              0.049544968,
+              0.01878086,
+              0.03274472,
+              0.017663997,
+              0.07483022,
+              0.02496901,
+              -0.011843339,
+              -0.11212756,
+              0.0070379525,
+              0.028099466,
+              -0.01746246,
+              0.08173482,
+              -0.007920462,
+              0.032095373,
+              -0.12300146,
+              0.033773854,
+              0.025873141,
+              -0.0045020077,
+              0.079493225,
+              0.0040725255,
+              0.03305898,
+              0.008061117,
+              0.0134422695,
+              -0.03292251,
+              0.031554114,
+              0.04013794,
+              0.0014983519,
+              0.030762345,
+              0.029481992,
+              0.041350223,
+              -0.047438618,
+              0.03944708,
+              -0.07526981,
+              0.037927423,
+              -0.026016014,
+              0.016933467,
+              0.0136799775,
+              0.0071263947,
+              -0.05386736,
+              -0.07443268,
+              -0.006070775,
+              0.024427462,
+              -0.039844982,
+              -0.020661902,
+              -0.033354662,
+              0.009005565,
+              0.12111172,
+              -0.028260944,
+              -0.036192853,
+              -0.021332363,
+              0.05333571,
+              0.05161245,
+              -0.01204843,
+              0.035563566,
+              0.05408247,
+              0.060722187,
+              0.07159865,
+              0.04299143,
+              0.008544481,
+              0.07421879,
+              0.00841512,
+              -0.036342908,
+              -0.008549791,
+              -0.08816386,
+              -0.049075164,
+              0.00029373015,
+              -0.05127952,
+              0.03586739,
+              -0.030380003,
+              -0.012642127,
+              0.018771531,
+              0.01711824,
+              -0.06644723,
+              0.023793438,
+              0.0010271219,
+              -0.01939443,
+              -0.053452212,
+              -0.017060323,
+              -0.062207118,
+              -0.05962535,
+              -0.012172617,
+              -0.013190802,
+              -0.037036054,
+              0.00082622556,
+              0.098088354,
+              0.024690514,
+              2.1767905e-33,
+              -0.010088812,
+              -0.016811697,
+              -0.042140447,
+              0.08837209,
+              -0.028899776,
+              -0.0048947735,
+              -0.082139015,
+              0.029238816,
+              -0.043079354,
+              -0.014153092,
+              -0.028387645,
+              0.025998218,
+              -0.017625,
+              0.046511114,
+              -0.005768211,
+              0.030010609,
+              0.011375536,
+              0.017426634,
+              0.055062976,
+              0.032230247,
+              -0.07995765,
+              0.032486655,
+              -0.060016844,
+              -0.011561194,
+              0.010211269,
+              0.046528235,
+              0.001191399,
+              0.0786961,
+              -0.0446158,
+              0.032789085,
+              0.0023115936,
+              -0.03886269,
+              -0.017663589,
+              0.07913024,
+              -0.004583343,
+              0.043521065,
+              -0.031589273,
+              0.008867868,
+              -0.05013296,
+              0.068929516,
+              0.043675046,
+              0.019968731,
+              -0.08471742,
+              -0.046864275,
+              -0.0068198936,
+              -0.026138468,
+              -0.05107216,
+              0.054374695,
+              0.03069186,
+              -0.010925094,
+              0.04721093,
+              -0.017387696,
+              -0.020754937,
+              -0.081763394,
+              -0.027709637,
+              0.035980806,
+              0.05396534,
+              0.044874854,
+              0.059699643,
+              0.041227758,
+              -0.06664364,
+              -0.09201654,
+              0.008915574,
+              0.025849758,
+              -0.038651932,
+              -0.0044070315,
+              -0.052066546,
+              0.027435115,
+              0.012089562,
+              0.048306923,
+              0.059854515,
+              0.097325735,
+              -0.053612895,
+              -0.07639326,
+              0.015773866,
+              -0.0444848,
+              -0.13214406,
+              -0.0702488,
+              -0.10134438,
+              -0.11905995,
+              -0.027714504,
+              0.006891868,
+              -0.0053650527,
+              0.054135524,
+              -0.111159205,
+              0.07835098,
+              0.03506018,
+              0.016036613,
+              0.021490784,
+              -0.061526407,
+              0.007425222,
+              0.04833579,
+              -0.01361202,
+              0.012450488,
+              -0.12729599,
+              -1.4009424e-08,
+              -0.040908325,
+              -0.01596458,
+              0.060048707,
+              0.03804525,
+              0.0663794,
+              0.04727275,
+              -0.016112225,
+              0.09687414,
+              -0.04424251,
+              -0.028799534,
+              -0.01294642,
+              0.013026413,
+              0.022404836,
+              0.04713173,
+              0.06402557,
+              0.12130648,
+              0.06062839,
+              0.10218965,
+              -0.0757528,
+              -0.023806982,
+              0.12489501,
+              -0.045460615,
+              0.09545599,
+              0.021262301,
+              0.03731495,
+              -0.075220875,
+              -0.0026194793,
+              0.0472452,
+              0.048499025,
+              0.12358729,
+              0.017998053,
+              0.013811017,
+              -0.035893846,
+              -0.051789004,
+              0.06182457,
+              0.05160056,
+              0.008895317,
+              -0.12500942,
+              0.016453298,
+              -0.08590811,
+              -0.071096726,
+              0.06987216,
+              -0.036072273,
+              -0.0053715096,
+              -0.048762616,
+              0.00081640907,
+              -0.021502526,
+              -0.061078615,
+              0.002485032,
+              -0.032720752,
+              0.045743283,
+              0.038934175,
+              -0.024666062,
+              0.025897244,
+              0.10301431,
+              -0.013001504,
+              0.04783332,
+              -0.07114252,
+              0.046031926,
+              0.080549754,
+              -0.10302451,
+              0.08449227,
+              0.028010191,
+              -0.03697792
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 6,
+          "total_tokens": 6
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/211b1562d4e6.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-08-04T22:55:11.15982Z",
+        "created_at": "2025-09-03T17:36:17.894986Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 498612042,
-        "load_duration": 71411834,
+        "total_duration": 363397458,
+        "load_duration": 86692791,
         "prompt_eval_count": 23,
-        "prompt_eval_duration": 102000000,
+        "prompt_eval_duration": 68658541,
         "eval_count": 6,
-        "eval_duration": 323000000,
+        "eval_duration": 207389084,
         "response": "Humans live on Earth.",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/23506e73bb9e.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "This is a test file 1"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.055990793,
+              0.076004684,
+              -0.09247725,
+              0.014340361,
+              0.058780864,
+              -0.032434482,
+              0.020954052,
+              0.028818125,
+              -0.06591213,
+              0.013541593,
+              0.12999941,
+              0.004603084,
+              -0.0069239275,
+              -0.055457443,
+              -0.047553156,
+              -0.029139794,
+              -0.12236376,
+              -0.05360872,
+              -0.014706594,
+              0.05984688,
+              0.034442738,
+              0.02076038,
+              -0.048697792,
+              0.0135388365,
+              0.058592733,
+              -0.003076384,
+              -0.031565297,
+              0.082541116,
+              -0.031259205,
+              -0.12057633,
+              0.038319625,
+              0.06574785,
+              0.06415721,
+              0.038382582,
+              0.12570712,
+              0.03108174,
+              0.10821103,
+              -0.0019794356,
+              -0.024704305,
+              0.028765837,
+              0.01268161,
+              -0.039844505,
+              0.043253522,
+              -0.015898596,
+              -0.0135526005,
+              -0.0050831717,
+              -0.007911988,
+              0.039783813,
+              0.0036548872,
+              -0.033632487,
+              -0.058547974,
+              0.0048877494,
+              -0.089586094,
+              -0.010457663,
+              0.059202507,
+              -0.020414542,
+              0.014278556,
+              0.013986488,
+              -0.0046022516,
+              0.0383391,
+              0.0048145773,
+              0.029772853,
+              -0.020863408,
+              0.018640704,
+              0.12422993,
+              -0.023236223,
+              -0.040323637,
+              -0.023598222,
+              -0.007448043,
+              -0.09083128,
+              -0.16859712,
+              0.01012451,
+              -0.035808884,
+              0.010595173,
+              -0.02050494,
+              0.0020821376,
+              -0.10925222,
+              0.00793264,
+              0.048889533,
+              -0.11391199,
+              -0.06072707,
+              -0.13435508,
+              0.0063265716,
+              -0.008838073,
+              -0.03153269,
+              0.099169336,
+              0.055310693,
+              0.0068571265,
+              -0.023463152,
+              -0.0031599961,
+              0.036782328,
+              0.014336826,
+              0.022220163,
+              0.047114056,
+              0.007079763,
+              0.06806425,
+              0.01851431,
+              0.040882625,
+              0.055058856,
+              0.09488346,
+              -0.015833577,
+              -7.924328e-05,
+              0.010821554,
+              0.09177704,
+              -0.07464829,
+              -0.06471165,
+              0.07013805,
+              -0.04499751,
+              0.057702336,
+              -0.0260911,
+              0.006323043,
+              -0.09500501,
+              -0.010549514,
+              -0.07887475,
+              0.039744847,
+              -0.04154404,
+              -0.055268157,
+              0.07540271,
+              -0.04667509,
+              0.036143072,
+              0.080297194,
+              -0.036381353,
+              -0.03477274,
+              0.01701203,
+              -0.047007203,
+              -0.06519774,
+              0.062141683,
+              -4.222482e-33,
+              -0.0017580023,
+              -0.09383388,
+              -0.02982657,
+              0.1257841,
+              0.03802007,
+              -0.03654342,
+              0.0060920226,
+              0.05906885,
+              -0.11074452,
+              0.005664566,
+              -0.0259852,
+              -0.074819505,
+              0.008342821,
+              0.027451068,
+              -0.05248069,
+              0.02401768,
+              -0.004380289,
+              0.039321493,
+              -0.04213744,
+              -0.027290314,
+              0.054677974,
+              0.02707243,
+              -0.03329442,
+              -0.060589895,
+              -0.050737355,
+              0.017969057,
+              -0.0035060972,
+              -0.04666249,
+              0.073946096,
+              0.01333894,
+              -0.0033873583,
+              -0.046544433,
+              -0.060105033,
+              0.03406923,
+              0.001542676,
+              0.039177947,
+              0.03989323,
+              -0.012346489,
+              -0.030511485,
+              -0.0019157606,
+              -0.014608986,
+              -0.012997742,
+              0.019522104,
+              -0.022349002,
+              0.074362256,
+              -0.053366993,
+              -0.023993475,
+              0.029225096,
+              0.027534606,
+              0.015111057,
+              -0.020442221,
+              0.043327376,
+              0.019660354,
+              0.017330697,
+              -0.0035011724,
+              0.019482937,
+              -0.0003428041,
+              0.0004143988,
+              -0.005117252,
+              0.06624799,
+              0.027922852,
+              0.041020587,
+              -0.067166425,
+              0.028737254,
+              -0.03478325,
+              -0.055551115,
+              -0.032713737,
+              -0.08099247,
+              0.09216284,
+              0.06395264,
+              -0.049168136,
+              -0.039908994,
+              0.036915958,
+              -0.001602359,
+              0.00033041168,
+              -0.026015632,
+              -0.005999889,
+              0.05474541,
+              -0.09568287,
+              -0.05186289,
+              -0.048838183,
+              -0.08639551,
+              -0.034023147,
+              -0.033257127,
+              -0.05651867,
+              -0.051131375,
+              0.00809173,
+              -0.08581851,
+              0.06507323,
+              -0.085427366,
+              0.027997404,
+              0.029847065,
+              -0.031673994,
+              -0.08560956,
+              0.1017672,
+              2.1855676e-33,
+              0.01160785,
+              0.077607885,
+              -0.017380483,
+              0.005239329,
+              0.0009684126,
+              0.06543702,
+              0.07256893,
+              -0.044318836,
+              -0.04749324,
+              0.14031002,
+              -0.025741624,
+              0.0057860985,
+              0.040946104,
+              -0.054880083,
+              0.074413285,
+              -0.023610368,
+              0.018364722,
+              -0.060585637,
+              -0.044149306,
+              0.0027854694,
+              -0.04580664,
+              0.1172219,
+              0.10268574,
+              0.07907412,
+              -0.0466143,
+              0.018618405,
+              0.029834948,
+              0.037265483,
+              0.02273822,
+              -0.0026589038,
+              0.041726097,
+              0.06439532,
+              -0.089163445,
+              0.018188318,
+              0.024064727,
+              -0.096389584,
+              0.08642254,
+              -0.05389359,
+              0.01923105,
+              0.045092683,
+              0.045125954,
+              0.09655961,
+              0.014908797,
+              0.059611585,
+              0.03066662,
+              0.05882299,
+              0.111484826,
+              0.016632542,
+              0.011590394,
+              -0.023702666,
+              -0.008617484,
+              -0.055030316,
+              0.047606383,
+              -0.014632687,
+              -0.014156344,
+              0.069926,
+              0.032047603,
+              0.042642817,
+              -0.053942375,
+              0.031047028,
+              0.009216673,
+              0.033024028,
+              -0.019033706,
+              0.005568194,
+              -0.014985451,
+              -0.09193244,
+              -0.03210824,
+              0.015367608,
+              0.029150328,
+              0.01250386,
+              -0.004827391,
+              0.023345906,
+              -0.028271332,
+              -0.08454125,
+              0.051068563,
+              -0.0133641455,
+              -0.029022738,
+              -0.02258452,
+              0.010884119,
+              -0.009810021,
+              0.049751773,
+              -0.0032637494,
+              -0.038813565,
+              0.027924104,
+              0.017925078,
+              0.005337612,
+              0.058691237,
+              0.09577674,
+              -0.014308608,
+              0.006972794,
+              -0.02733344,
+              0.06912433,
+              0.05727631,
+              0.03206042,
+              0.0042422824,
+              -1.6766318e-08,
+              -0.036354303,
+              -0.09146416,
+              -0.026319364,
+              -0.007941995,
+              -0.024127059,
+              0.09896698,
+              -0.04723083,
+              -0.03767135,
+              -0.029419973,
+              -0.022513283,
+              0.04125822,
+              -0.0011487947,
+              -0.05570366,
+              0.020679709,
+              -0.038118906,
+              -0.0524994,
+              -0.02624128,
+              -0.05336954,
+              -0.040593866,
+              -0.0073642326,
+              -0.0014442836,
+              0.02714257,
+              0.027141048,
+              0.00932513,
+              -0.00026505854,
+              0.038233075,
+              0.037096914,
+              0.08405413,
+              -0.06340637,
+              -0.014856458,
+              0.05038612,
+              0.06703033,
+              0.027668556,
+              -0.04360097,
+              -0.012041474,
+              0.08500689,
+              0.111594744,
+              0.1046117,
+              0.019726463,
+              -0.0003025109,
+              -0.04110389,
+              0.009575226,
+              -0.05285304,
+              -0.0026365265,
+              -0.031144748,
+              -0.08860188,
+              -0.06762232,
+              -0.07451522,
+              -0.053012833,
+              -0.09560941,
+              -0.05273455,
+              0.013032144,
+              0.0029190276,
+              0.041905046,
+              -0.04522114,
+              0.016730292,
+              0.017214278,
+              0.021578068,
+              -0.03718778,
+              0.02353425,
+              0.052041385,
+              0.06444499,
+              0.02387539,
+              -0.025236009
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 6,
+          "total_tokens": 6
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/27463384d1a3.json

@@ -0,0 +1,56 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://localhost:8080/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "Qwen/Qwen3-0.6B",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello, world!"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "Qwen/Qwen3-0.6B"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "<think>\nOkay, the user just said \"Hello, world!\" so I need to respond in a friendly way. My prompt says to respond in the same style, so I should start with \"Hello, world!\" but maybe add some helpful information. Let me think. Since the user is probably testing or just sharing, a simple \"Hello, world!\" with a question would be best for user interaction. I'll make sure to keep it positive and open-ended.\n</think>\n\nHello, world! \ud83d\ude0a What do you need today?",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 1757550395,
+        "model": "Qwen/Qwen3-0.6B",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "3.3.5-dev0-sha-1b90c50",
+        "usage": {
+          "completion_tokens": 108,
+          "prompt_tokens": 12,
+          "total_tokens": 120,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/2afe3b38ca01.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:01.887809Z",
+          "created_at": "2025-09-03T17:37:50.436472Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:01.942369Z",
+          "created_at": "2025-09-03T17:37:50.478138Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:01.99605Z",
+          "created_at": "2025-09-03T17:37:50.519952Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.049974Z",
+          "created_at": "2025-09-03T17:37:50.561433Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.102027Z",
+          "created_at": "2025-09-03T17:37:50.603624Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.158416Z",
+          "created_at": "2025-09-03T17:37:50.645851Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.211753Z",
+          "created_at": "2025-09-03T17:37:50.688403Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.265564Z",
+          "created_at": "2025-09-03T17:37:50.72991Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.31618Z",
+          "created_at": "2025-09-03T17:37:50.771635Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.370325Z",
+          "created_at": "2025-09-03T17:37:50.813711Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.424667Z",
+          "created_at": "2025-09-03T17:37:50.856201Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.47913Z",
+          "created_at": "2025-09-03T17:37:50.899048Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,15 +238,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:02.536984Z",
+          "created_at": "2025-09-03T17:37:50.94069Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1042724125,
-          "load_duration": 86161375,
+          "total_duration": 688370708,
+          "load_duration": 107469833,
           "prompt_eval_count": 399,
-          "prompt_eval_duration": 305000000,
+          "prompt_eval_duration": 74988334,
           "eval_count": 13,
-          "eval_duration": 650000000,
+          "eval_duration": 505216458,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/2b2ad549510d.json

@@ -0,0 +1,448 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://shan-mfbb618r-eastus2.cognitiveservices.azure.com/openai/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-5-mini",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello, world!"
+        }
+      ],
+      "stream": true
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-5-mini"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "",
+          "choices": [],
+          "created": 0,
+          "model": "",
+          "object": "",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null,
+          "prompt_filter_results": [
+            {
+              "prompt_index": 0,
+              "content_filter_results": {}
+            }
+          ]
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": "Hello",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": ",",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " world",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": "!",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " Hi",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " \u2014",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " how",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " can",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " I",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " help",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " you",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": " today",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": "?",
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-CECIgeXOClAuSm8xHAS6CYQ87lB8O",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": null
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null,
+              "content_filter_results": {}
+            }
+          ],
+          "created": 1757499910,
+          "model": "gpt-5-mini-2025-08-07",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      }
+    ],
+    "is_streaming": true
+  }
+}

tests/integration/recordings/responses/2d187a11704c.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:11.938867Z",
+          "created_at": "2025-09-03T17:37:56.566151Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:11.991247Z",
+          "created_at": "2025-09-03T17:37:56.609308Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.043953Z",
+          "created_at": "2025-09-03T17:37:56.651314Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.096001Z",
+          "created_at": "2025-09-03T17:37:56.693185Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.150454Z",
+          "created_at": "2025-09-03T17:37:56.734643Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.201249Z",
+          "created_at": "2025-09-03T17:37:56.776343Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.252534Z",
+          "created_at": "2025-09-03T17:37:56.81705Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.30063Z",
+          "created_at": "2025-09-03T17:37:56.857959Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.351034Z",
+          "created_at": "2025-09-03T17:37:56.899424Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.405032Z",
+          "created_at": "2025-09-03T17:37:56.939218Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.462645Z",
+          "created_at": "2025-09-03T17:37:56.980065Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.520337Z",
+          "created_at": "2025-09-03T17:37:57.02214Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,7 +238,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.575809Z",
+          "created_at": "2025-09-03T17:37:57.0628Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -256,7 +256,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.633724Z",
+          "created_at": "2025-09-03T17:37:57.106061Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -274,7 +274,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.683133Z",
+          "created_at": "2025-09-03T17:37:57.1492Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -292,7 +292,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.734309Z",
+          "created_at": "2025-09-03T17:37:57.190075Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -310,7 +310,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.785917Z",
+          "created_at": "2025-09-03T17:37:57.23178Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -328,7 +328,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.835705Z",
+          "created_at": "2025-09-03T17:37:57.272738Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -346,7 +346,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.886509Z",
+          "created_at": "2025-09-03T17:37:57.313855Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -364,7 +364,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.937134Z",
+          "created_at": "2025-09-03T17:37:57.354964Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -382,7 +382,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:12.988532Z",
+          "created_at": "2025-09-03T17:37:57.395971Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -400,7 +400,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.041798Z",
+          "created_at": "2025-09-03T17:37:57.438471Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -418,7 +418,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.095443Z",
+          "created_at": "2025-09-03T17:37:57.479796Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -436,7 +436,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.151402Z",
+          "created_at": "2025-09-03T17:37:57.520641Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -454,7 +454,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.203462Z",
+          "created_at": "2025-09-03T17:37:57.561511Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -472,7 +472,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.254567Z",
+          "created_at": "2025-09-03T17:37:57.602875Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -490,7 +490,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.305865Z",
+          "created_at": "2025-09-03T17:37:57.643406Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -508,7 +508,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.357658Z",
+          "created_at": "2025-09-03T17:37:57.684279Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -526,7 +526,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.407773Z",
+          "created_at": "2025-09-03T17:37:57.725699Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -544,7 +544,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.458919Z",
+          "created_at": "2025-09-03T17:37:57.766658Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -562,7 +562,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.510456Z",
+          "created_at": "2025-09-03T17:37:57.80738Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -580,7 +580,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.565948Z",
+          "created_at": "2025-09-03T17:37:57.848466Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -598,7 +598,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.619155Z",
+          "created_at": "2025-09-03T17:37:57.889056Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -616,7 +616,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.672754Z",
+          "created_at": "2025-09-03T17:37:57.931554Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -634,7 +634,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.729473Z",
+          "created_at": "2025-09-03T17:37:57.974754Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -652,7 +652,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.788666Z",
+          "created_at": "2025-09-03T17:37:58.016978Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -670,7 +670,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.850575Z",
+          "created_at": "2025-09-03T17:37:58.057942Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -688,7 +688,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.904807Z",
+          "created_at": "2025-09-03T17:37:58.099015Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -706,7 +706,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:13.958524Z",
+          "created_at": "2025-09-03T17:37:58.140531Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -724,7 +724,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.011742Z",
+          "created_at": "2025-09-03T17:37:58.181382Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -742,7 +742,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.064933Z",
+          "created_at": "2025-09-03T17:37:58.223318Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -760,7 +760,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.116454Z",
+          "created_at": "2025-09-03T17:37:58.26358Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -778,7 +778,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.172682Z",
+          "created_at": "2025-09-03T17:37:58.305496Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -796,7 +796,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.227654Z",
+          "created_at": "2025-09-03T17:37:58.347254Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -814,7 +814,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.282068Z",
+          "created_at": "2025-09-03T17:37:58.390044Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -832,7 +832,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.334565Z",
+          "created_at": "2025-09-03T17:37:58.430867Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -850,7 +850,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.383532Z",
+          "created_at": "2025-09-03T17:37:58.471376Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -868,7 +868,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.432138Z",
+          "created_at": "2025-09-03T17:37:58.51208Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -886,7 +886,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.480995Z",
+          "created_at": "2025-09-03T17:37:58.553226Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -904,7 +904,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.531968Z",
+          "created_at": "2025-09-03T17:37:58.594787Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -922,7 +922,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.584044Z",
+          "created_at": "2025-09-03T17:37:58.63466Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -940,7 +940,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.635691Z",
+          "created_at": "2025-09-03T17:37:58.674628Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -958,7 +958,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.68837Z",
+          "created_at": "2025-09-03T17:37:58.714616Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -976,7 +976,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.73985Z",
+          "created_at": "2025-09-03T17:37:58.754906Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -994,7 +994,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.792412Z",
+          "created_at": "2025-09-03T17:37:58.795048Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1012,7 +1012,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.845872Z",
+          "created_at": "2025-09-03T17:37:58.835297Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1030,7 +1030,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.900102Z",
+          "created_at": "2025-09-03T17:37:58.875738Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1048,7 +1048,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:14.954589Z",
+          "created_at": "2025-09-03T17:37:58.91604Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1066,7 +1066,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.006629Z",
+          "created_at": "2025-09-03T17:37:58.956596Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1084,7 +1084,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.058561Z",
+          "created_at": "2025-09-03T17:37:58.996664Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1102,7 +1102,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.111954Z",
+          "created_at": "2025-09-03T17:37:59.037796Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1120,7 +1120,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.169173Z",
+          "created_at": "2025-09-03T17:37:59.078586Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1138,7 +1138,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.222569Z",
+          "created_at": "2025-09-03T17:37:59.119448Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1156,7 +1156,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.275795Z",
+          "created_at": "2025-09-03T17:37:59.160318Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1174,7 +1174,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.3327Z",
+          "created_at": "2025-09-03T17:37:59.201852Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1192,7 +1192,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.389931Z",
+          "created_at": "2025-09-03T17:37:59.243763Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1210,7 +1210,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.442349Z",
+          "created_at": "2025-09-03T17:37:59.284948Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1228,7 +1228,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.494175Z",
+          "created_at": "2025-09-03T17:37:59.325598Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1246,7 +1246,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.545764Z",
+          "created_at": "2025-09-03T17:37:59.366289Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1264,7 +1264,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.599099Z",
+          "created_at": "2025-09-03T17:37:59.406764Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1282,7 +1282,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.649852Z",
+          "created_at": "2025-09-03T17:37:59.447922Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1300,7 +1300,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.698222Z",
+          "created_at": "2025-09-03T17:37:59.488486Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1318,7 +1318,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.747168Z",
+          "created_at": "2025-09-03T17:37:59.529Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1336,7 +1336,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.797196Z",
+          "created_at": "2025-09-03T17:37:59.569417Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1354,7 +1354,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.845587Z",
+          "created_at": "2025-09-03T17:37:59.610542Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1372,7 +1372,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.897171Z",
+          "created_at": "2025-09-03T17:37:59.651411Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1390,7 +1390,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.944524Z",
+          "created_at": "2025-09-03T17:37:59.69241Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1408,7 +1408,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:15.994467Z",
+          "created_at": "2025-09-03T17:37:59.732339Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1426,7 +1426,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.045224Z",
+          "created_at": "2025-09-03T17:37:59.772462Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1444,7 +1444,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.093853Z",
+          "created_at": "2025-09-03T17:37:59.812507Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1462,7 +1462,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.144847Z",
+          "created_at": "2025-09-03T17:37:59.852762Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1480,7 +1480,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.197888Z",
+          "created_at": "2025-09-03T17:37:59.892984Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1498,7 +1498,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.250854Z",
+          "created_at": "2025-09-03T17:37:59.933555Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1516,7 +1516,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.301995Z",
+          "created_at": "2025-09-03T17:37:59.973778Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1534,7 +1534,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.352508Z",
+          "created_at": "2025-09-03T17:38:00.014923Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1552,7 +1552,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.40259Z",
+          "created_at": "2025-09-03T17:38:00.057464Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1570,7 +1570,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.453514Z",
+          "created_at": "2025-09-03T17:38:00.09902Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1588,7 +1588,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.50378Z",
+          "created_at": "2025-09-03T17:38:00.140492Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1606,7 +1606,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.554395Z",
+          "created_at": "2025-09-03T17:38:00.180239Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1624,7 +1624,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.605795Z",
+          "created_at": "2025-09-03T17:38:00.220364Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1642,7 +1642,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.656313Z",
+          "created_at": "2025-09-03T17:38:00.26097Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1660,7 +1660,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.706438Z",
+          "created_at": "2025-09-03T17:38:00.301228Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1678,7 +1678,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.756444Z",
+          "created_at": "2025-09-03T17:38:00.341631Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1696,7 +1696,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.807687Z",
+          "created_at": "2025-09-03T17:38:00.383006Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1714,7 +1714,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.85835Z",
+          "created_at": "2025-09-03T17:38:00.423509Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1732,7 +1732,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.909311Z",
+          "created_at": "2025-09-03T17:38:00.464702Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1750,7 +1750,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:16.959327Z",
+          "created_at": "2025-09-03T17:38:00.505914Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1768,7 +1768,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:17.010211Z",
+          "created_at": "2025-09-03T17:38:00.546505Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1786,7 +1786,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:17.061365Z",
+          "created_at": "2025-09-03T17:38:00.587839Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -1804,15 +1804,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:17.111956Z",
+          "created_at": "2025-09-03T17:38:00.629018Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 5499672375,
-          "load_duration": 58161750,
+          "total_duration": 4303339291,
+          "load_duration": 156231250,
           "prompt_eval_count": 36,
-          "prompt_eval_duration": 266000000,
+          "prompt_eval_duration": 81909875,
           "eval_count": 100,
-          "eval_duration": 5174000000,
+          "eval_duration": 4064559292,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/382c2f22274c.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -22,14 +22,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-339",
+        "id": "chatcmpl-442",
         "choices": [
           {
             "finish_reason": "length",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I can guide you through the process, but please note that this is not an official OpenAI API call. OpenAI's API terms and conditions prohibit using their models for malicious purposes.\n\nTo test a model like \"text-temperature\" with a temperature of 0 (i.e., no noise or randomness), we'll need to use a third-party library that connects to the OpenAI API. One such library is `transformers`.\n\nFirst, you need to install the `transformers` and `",
+              "content": "I can guide you on how to use the `test-temperature` parameter with OpenAI's API, but please note that using a temperature of 0 may not produce meaningful results. Temperature is a hyperparameter that controls the level of randomness in the model's output.\n\nOpenAI's API uses a variant of the GPT-3 model, which is trained on a large corpus of text data. The `test-temperature` parameter allows you to adjust the level of randomness in the model's output",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -39,7 +39,7 @@
             }
           }
         ],
-        "created": 1754510065,
+        "created": 1756921254,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,

tests/integration/recordings/responses/3c0bf9ba81b2.json

@@ -20,14 +20,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-651",
+        "id": "chatcmpl-334",
         "choices": [
           {
             "finish_reason": "length",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I'm ready to help",
+              "content": "It looks like we've",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -37,7 +37,7 @@
             }
           }
         ],
-        "created": 1755294941,
+        "created": 1756921086,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,

tests/integration/recordings/responses/3c3f13cb7794.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.338232Z",
+          "created_at": "2025-09-03T17:36:18.136699Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.39419Z",
+          "created_at": "2025-09-03T17:36:18.177622Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.445346Z",
+          "created_at": "2025-09-03T17:36:18.218104Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.496701Z",
+          "created_at": "2025-09-03T17:36:18.258837Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.546804Z",
+          "created_at": "2025-09-03T17:36:18.299715Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.601009Z",
+          "created_at": "2025-09-03T17:36:18.341602Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.652788Z",
+          "created_at": "2025-09-03T17:36:18.385504Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.703325Z",
+          "created_at": "2025-09-03T17:36:18.429427Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.754033Z",
+          "created_at": "2025-09-03T17:36:18.473547Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.804654Z",
+          "created_at": "2025-09-03T17:36:18.516327Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,15 +201,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:11.854841Z",
+          "created_at": "2025-09-03T17:36:18.559332Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 652371000,
-          "load_duration": 42086042,
+          "total_duration": 628034000,
+          "load_duration": 116384417,
           "prompt_eval_count": 26,
-          "prompt_eval_duration": 78000000,
+          "prompt_eval_duration": 87798792,
           "eval_count": 11,
-          "eval_duration": 531000000,
+          "eval_duration": 423189583,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/3ca695048bee.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -39,7 +39,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-490",
+          "id": "chatcmpl-3",
           "choices": [
             {
               "delta": {
@@ -50,7 +50,7 @@
                 "tool_calls": [
                   {
                     "index": 0,
-                    "id": "call_rolv1ozt",
+                    "id": "call_3kigugt3",
                     "function": {
                       "arguments": "{\"city\":\"Tokyo\"}",
                       "name": "get_weather"
@@ -64,7 +64,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081852,
+          "created": 1756921361,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -75,7 +75,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-490",
+          "id": "chatcmpl-3",
           "choices": [
             {
               "delta": {
@@ -85,12 +85,12 @@
                 "role": "assistant",
                 "tool_calls": null
               },
-              "finish_reason": "stop",
+              "finish_reason": "tool_calls",
               "index": 0,
               "logprobs": null
             }
           ],
-          "created": 1754081852,
+          "created": 1756921361,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,

tests/integration/recordings/responses/3dff18060ebc.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "The secret string is foobazbar."
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.060630284,
+              0.06372823,
+              -0.059383437,
+              -0.010313639,
+              -0.11985778,
+              0.033409074,
+              0.056847293,
+              -0.0064553,
+              0.029896382,
+              -0.05037607,
+              0.015193001,
+              -0.0634204,
+              0.015119892,
+              -0.08354324,
+              0.0092577925,
+              0.044272587,
+              -0.024397198,
+              -0.05100177,
+              -0.028086444,
+              -0.07390362,
+              0.07088186,
+              0.08101153,
+              0.006050408,
+              -0.043090094,
+              0.010714593,
+              -0.01581376,
+              0.0351736,
+              0.06538307,
+              0.03639655,
+              -0.05625738,
+              0.073681176,
+              0.04730274,
+              0.067169026,
+              -0.01207242,
+              -0.018193275,
+              0.0042488067,
+              0.029168725,
+              0.0067459582,
+              0.037927665,
+              0.0024767139,
+              0.014044963,
+              0.022671249,
+              -0.090508185,
+              0.041952047,
+              -0.07933115,
+              0.031992197,
+              -0.038355146,
+              0.037013844,
+              -0.0036946274,
+              -0.016986867,
+              0.03696087,
+              -0.07697335,
+              -0.020080294,
+              0.07733012,
+              0.04521822,
+              -0.007816803,
+              -0.0058926586,
+              0.009962128,
+              0.033492323,
+              0.09000152,
+              0.016161384,
+              0.036999356,
+              -0.039193578,
+              -0.010969346,
+              0.023929566,
+              -0.03698458,
+              -0.008227196,
+              0.018780757,
+              -0.0006967325,
+              -0.062018193,
+              -0.030388007,
+              -0.037649162,
+              -0.04654288,
+              0.038450293,
+              -0.010377299,
+              -0.032971557,
+              0.013547814,
+              -0.059036925,
+              0.0630603,
+              0.0159564,
+              -0.04845087,
+              -0.069917254,
+              -0.022502322,
+              0.04408022,
+              0.03618941,
+              0.060470726,
+              -0.04313285,
+              0.028797466,
+              0.0062393937,
+              0.01027349,
+              -0.078714885,
+              -0.091531575,
+              0.04391341,
+              0.013202597,
+              -0.0037814155,
+              0.0102497,
+              0.020225797,
+              0.05634384,
+              -0.09700619,
+              0.06577961,
+              0.047118917,
+              0.01876648,
+              0.12445029,
+              -0.06447121,
+              -0.012632697,
+              0.016056264,
+              0.08604982,
+              0.024878234,
+              0.10627678,
+              -0.043176394,
+              -0.046339765,
+              -0.03149599,
+              -0.001784808,
+              -0.023469802,
+              -0.05079461,
+              0.0046657966,
+              0.043237828,
+              0.057146583,
+              -0.065833576,
+              0.032975562,
+              -0.028763266,
+              0.037831448,
+              0.00017829033,
+              0.043322463,
+              -0.13265091,
+              0.0263673,
+              -0.04247752,
+              -3.3340873e-33,
+              -0.0022191573,
+              0.050657377,
+              0.028066125,
+              -0.033898965,
+              -0.0045730886,
+              -0.034653578,
+              -0.08628417,
+              0.043108672,
+              0.01022734,
+              0.044009056,
+              -0.03020062,
+              -0.0936044,
+              -0.06522928,
+              -0.059762992,
+              0.037560984,
+              -0.025942331,
+              -0.06655938,
+              0.0043691625,
+              0.018846871,
+              -0.035582166,
+              0.02240012,
+              0.08943218,
+              0.033568345,
+              -0.11379316,
+              0.03822112,
+              -0.044403847,
+              0.10261262,
+              -0.07330182,
+              0.089390896,
+              0.056668896,
+              -0.009407597,
+              -0.0646505,
+              0.016652016,
+              0.007326742,
+              0.005187682,
+              0.0051324354,
+              -0.013595071,
+              -0.04918112,
+              -0.06672084,
+              0.010838405,
+              0.04638185,
+              -0.11490209,
+              -0.055054087,
+              0.040443793,
+              -0.032746885,
+              0.03498173,
+              -0.023567867,
+              -0.012213799,
+              0.048050664,
+              0.01159698,
+              0.007860181,
+              0.03801084,
+              -0.027765153,
+              0.003296162,
+              -0.0033349432,
+              0.006083357,
+              0.03200884,
+              0.048306234,
+              0.013800832,
+              0.036165927,
+              -0.022672432,
+              0.09197581,
+              0.029846204,
+              0.08112345,
+              -0.08677228,
+              -0.028041098,
+              0.0556574,
+              -0.030357547,
+              -0.016538681,
+              0.031826265,
+              -0.07586954,
+              -0.009915978,
+              0.028101236,
+              0.002207158,
+              -0.10496646,
+              -0.023673821,
+              -0.024204832,
+              -0.0003132271,
+              0.0016462951,
+              -0.037603874,
+              0.025533162,
+              -0.05221861,
+              0.021656586,
+              0.099111386,
+              -0.06896361,
+              -0.018568028,
+              0.07245527,
+              -0.10582686,
+              -0.08505038,
+              -0.029969748,
+              -0.015717981,
+              -0.056855034,
+              -0.02698479,
+              -0.06410572,
+              0.0057078917,
+              1.2902391e-33,
+              0.05490771,
+              -0.036417797,
+              -0.0023541928,
+              -0.03591478,
+              0.106852315,
+              -0.04931468,
+              0.037884213,
+              0.050633065,
+              -0.083874516,
+              -0.018756155,
+              0.0036251817,
+              0.028974183,
+              -0.0027879397,
+              -0.036439158,
+              0.11148004,
+              0.051007163,
+              0.040258586,
+              0.09245398,
+              -0.01367112,
+              -0.070999645,
+              -0.043213032,
+              -0.060117763,
+              -0.03019449,
+              0.009107182,
+              -0.044254936,
+              0.04843456,
+              0.117205575,
+              -0.009833911,
+              0.0023962231,
+              0.09339494,
+              -0.059902366,
+              0.0101377955,
+              -0.03777244,
+              -0.04344207,
+              -0.14677393,
+              -0.022666233,
+              -0.008934328,
+              -0.02157697,
+              -0.021902358,
+              -0.06611372,
+              0.016243221,
+              0.062620856,
+              0.01056146,
+              0.04721975,
+              -0.087221384,
+              0.009420561,
+              -0.017691165,
+              -0.03847053,
+              0.010398396,
+              0.022942957,
+              0.099518456,
+              -0.021421565,
+              0.0016765085,
+              -0.039359514,
+              0.01641369,
+              0.039669517,
+              -0.119695365,
+              0.009885617,
+              0.003855461,
+              0.018273395,
+              -0.0454586,
+              0.0020496584,
+              0.024263415,
+              0.016978405,
+              0.06884217,
+              -0.027432522,
+              -0.01813802,
+              0.053840507,
+              -0.028815664,
+              -0.045221787,
+              0.11472852,
+              0.019796453,
+              -0.05785514,
+              0.016556906,
+              -0.07362942,
+              0.04025756,
+              -0.01510899,
+              0.0067040483,
+              -0.049666926,
+              0.045941774,
+              0.077951804,
+              -0.042951427,
+              0.021852365,
+              0.063826546,
+              0.08110754,
+              -0.070652775,
+              -0.03245094,
+              0.09259784,
+              -0.020451743,
+              0.0701599,
+              -0.020740295,
+              0.09339449,
+              -0.051164806,
+              0.039440546,
+              0.02560772,
+              -1.6767814e-08,
+              0.001529873,
+              0.0080792755,
+              -0.017666567,
+              -0.034070052,
+              0.06805411,
+              0.07387949,
+              -0.07592055,
+              -0.11369049,
+              -0.022008128,
+              0.009088418,
+              0.03108134,
+              -0.0056734695,
+              -0.0462051,
+              0.0037219985,
+              0.013269294,
+              -0.03213892,
+              -0.05557376,
+              -0.010602884,
+              0.006751397,
+              -0.025462827,
+              -0.0836812,
+              0.08886153,
+              0.005159859,
+              -0.051621262,
+              -0.051873572,
+              0.039706588,
+              -0.042155124,
+              0.057125967,
+              0.088910565,
+              0.049736783,
+              0.04144574,
+              0.094677895,
+              -0.037107926,
+              -0.06845684,
+              -0.061673928,
+              0.09891817,
+              -0.05952751,
+              -0.0331722,
+              -0.026014913,
+              0.077612035,
+              0.056150436,
+              0.010709955,
+              0.018974187,
+              0.056079865,
+              -0.041700333,
+              -0.02731697,
+              0.10184176,
+              -0.036189064,
+              -0.029914921,
+              -0.043333948,
+              0.043660097,
+              0.018800316,
+              -0.0042763646,
+              0.055898346,
+              -0.0034344571,
+              0.060258396,
+              -0.1337251,
+              0.008184424,
+              -0.031549457,
+              0.022398692,
+              0.037932154,
+              0.024529235,
+              0.068037644,
+              0.07021777
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 9,
+          "total_tokens": 9
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/417020320684.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "Python programming language"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.063880146,
+              0.013411989,
+              -0.054502595,
+              0.01193493,
+              -0.074262686,
+              -0.13344447,
+              0.04294062,
+              0.045387108,
+              -0.06949706,
+              -0.035939943,
+              0.01200873,
+              0.0068830596,
+              0.08886977,
+              0.0026030506,
+              0.032482542,
+              -0.007821568,
+              -0.05044649,
+              0.006662123,
+              0.027794942,
+              -0.12791364,
+              0.00062353734,
+              0.045270294,
+              -0.03605076,
+              0.044243146,
+              0.0129354475,
+              -0.0092799105,
+              0.011904844,
+              0.026060482,
+              0.020055141,
+              -0.03368774,
+              -0.028043076,
+              0.087557025,
+              0.059002083,
+              0.053893365,
+              0.02027196,
+              0.06840361,
+              -0.03180594,
+              -0.087597735,
+              -0.11277839,
+              0.022651086,
+              -0.09037903,
+              -0.0033202847,
+              -0.040132593,
+              -0.034084503,
+              -0.032953303,
+              0.02925268,
+              -0.03903928,
+              0.04551951,
+              -0.0331016,
+              -0.006518362,
+              -0.09629851,
+              -0.011739161,
+              -0.052575007,
+              -0.064773224,
+              0.031043475,
+              -0.012586444,
+              0.09737276,
+              0.005224713,
+              -0.035071153,
+              -0.1404299,
+              -0.06678175,
+              0.03654573,
+              -0.039277818,
+              0.07014256,
+              -0.0010227569,
+              -0.026846789,
+              -0.0175696,
+              0.03044068,
+              0.06403526,
+              -0.031643596,
+              -0.14598879,
+              -0.045400888,
+              -0.018469285,
+              0.06689445,
+              0.030553635,
+              -0.12255281,
+              0.061046645,
+              -0.05678168,
+              -0.005118667,
+              -0.0087622,
+              0.006514719,
+              -0.016424034,
+              -0.033650044,
+              0.08491301,
+              -0.00029260007,
+              -0.07339515,
+              0.038627055,
+              0.15695965,
+              0.010035773,
+              0.025318887,
+              -0.0021428047,
+              -0.04613549,
+              0.06244243,
+              -0.019905778,
+              -0.05471386,
+              0.09796629,
+              0.0384793,
+              -0.072424814,
+              -0.038704097,
+              0.07158691,
+              0.007360897,
+              -0.05120446,
+              0.0313513,
+              -0.032230332,
+              0.039326303,
+              -0.009643992,
+              0.069905065,
+              -0.052026685,
+              0.049440835,
+              -0.04272916,
+              -0.0037707465,
+              -0.04155246,
+              -0.0561972,
+              -0.03340213,
+              0.05105359,
+              0.038616214,
+              -0.0029470131,
+              0.08188407,
+              -0.0035886324,
+              0.04530431,
+              0.0068888925,
+              0.016499842,
+              0.016347302,
+              0.007283021,
+              -0.021663606,
+              -0.0046215886,
+              -0.007931065,
+              -4.1536508e-33,
+              -0.045777988,
+              -0.050903402,
+              -0.038634304,
+              0.0100991195,
+              0.070007294,
+              -0.025182785,
+              0.1050647,
+              -0.0049731904,
+              -0.064141616,
+              -0.047639705,
+              0.012718577,
+              0.05198462,
+              -0.016051587,
+              0.08170543,
+              0.024008816,
+              -0.020879291,
+              0.045706064,
+              0.091577366,
+              0.02512945,
+              0.019055998,
+              0.048144504,
+              0.097951256,
+              0.034154113,
+              0.03543114,
+              0.011410896,
+              -0.043446988,
+              -0.0041784984,
+              -0.05564714,
+              0.01147717,
+              0.0071039577,
+              -0.06426582,
+              -0.020623188,
+              -0.0045247558,
+              -0.012943628,
+              0.02658834,
+              -0.012385487,
+              0.008399212,
+              -0.06824828,
+              0.04683057,
+              -0.04165085,
+              -0.025662417,
+              -0.0038799767,
+              0.05007075,
+              -0.008117481,
+              -0.023308154,
+              0.023914568,
+              0.0015741173,
+              0.046142872,
+              -0.06898886,
+              0.041611847,
+              0.0045286645,
+              -0.047628563,
+              0.054236773,
+              0.06972688,
+              -0.016889753,
+              0.04806098,
+              0.012714234,
+              0.0022186628,
+              -0.006355918,
+              -0.031550523,
+              0.023726372,
+              0.06859327,
+              0.077228814,
+              -0.01227583,
+              0.03901903,
+              0.034360897,
+              0.03032876,
+              0.058690928,
+              0.08030179,
+              0.06976231,
+              -0.09047136,
+              0.02376998,
+              -0.008751518,
+              0.038334776,
+              -0.02751323,
+              0.023137644,
+              0.027101006,
+              -0.08135271,
+              -0.010334998,
+              0.04730408,
+              -0.02033998,
+              -0.026008504,
+              -0.017415512,
+              -0.0035714875,
+              -0.018727385,
+              -0.037389226,
+              0.041064497,
+              0.05317889,
+              -0.0055602547,
+              -0.058561854,
+              -0.072036326,
+              -0.075019896,
+              0.04825644,
+              0.011348427,
+              -0.02259257,
+              1.3515749e-33,
+              0.006240622,
+              0.031606406,
+              -0.036119435,
+              -0.0016494404,
+              -0.08255665,
+              -0.06069396,
+              0.059934463,
+              0.014492232,
+              0.059514895,
+              0.027053975,
+              -0.011601325,
+              -0.057609312,
+              0.10365583,
+              -0.002784741,
+              0.07693759,
+              0.019432511,
+              -0.052210074,
+              0.015158053,
+              -0.0012768542,
+              0.027789148,
+              -0.115292676,
+              0.047323048,
+              -0.07599195,
+              -0.074344486,
+              -0.029194841,
+              -0.020079462,
+              -0.034749795,
+              -0.05769437,
+              -0.0301632,
+              0.04749987,
+              0.012206333,
+              0.011497502,
+              -0.051970575,
+              0.05972769,
+              0.03281016,
+              0.0013676677,
+              0.057720944,
+              -0.041179247,
+              -0.02150875,
+              -0.0067487382,
+              0.1419711,
+              0.05795878,
+              0.010094941,
+              0.09603845,
+              0.014521089,
+              0.02133803,
+              -0.07551916,
+              0.07887724,
+              -0.04273237,
+              -0.06601746,
+              -0.038729392,
+              -0.008161129,
+              0.015012324,
+              -0.049418066,
+              -0.037083283,
+              -0.02378242,
+              0.03743137,
+              0.008194503,
+              -0.086978436,
+              -0.05960285,
+              -0.07732487,
+              -0.056507926,
+              0.029065313,
+              0.0073954053,
+              -0.077878684,
+              0.0026059505,
+              -0.10405392,
+              -0.04738624,
+              -0.015872862,
+              -0.11591199,
+              0.09724705,
+              0.0049243565,
+              -0.010273523,
+              0.0066429917,
+              -0.060295314,
+              0.02550513,
+              -0.052950058,
+              -0.0038489713,
+              -0.050250847,
+              0.07679287,
+              0.046089787,
+              0.007386997,
+              0.0046740095,
+              0.07385862,
+              -0.07792065,
+              0.0013675193,
+              0.013730894,
+              0.05658653,
+              0.021934126,
+              0.007195913,
+              0.0076705213,
+              0.10221154,
+              0.060060997,
+              0.036779005,
+              -0.037765697,
+              -1.187368e-08,
+              -0.00885571,
+              0.01760442,
+              0.062224448,
+              0.032051455,
+              -0.011581793,
+              0.051908698,
+              -0.011685676,
+              -0.06391574,
+              -0.029866237,
+              0.03258576,
+              0.0055078953,
+              -0.012040446,
+              -0.054406017,
+              -0.056690563,
+              -0.030638037,
+              0.14276367,
+              0.028526368,
+              -0.028743364,
+              0.019917691,
+              0.025652615,
+              0.073813364,
+              -0.0066998666,
+              0.0061508445,
+              0.09610696,
+              -0.08799916,
+              -0.0089272335,
+              0.03823298,
+              0.04832936,
+              0.018829934,
+              -0.10534708,
+              0.048226915,
+              -0.02225069,
+              0.020491786,
+              0.014641141,
+              0.030794447,
+              -0.029119467,
+              0.008283775,
+              -0.04506887,
+              0.0025344177,
+              0.021756247,
+              -0.008108281,
+              0.00904927,
+              -0.013340866,
+              -0.014037631,
+              0.06845187,
+              0.045173325,
+              -0.034587316,
+              -0.07275669,
+              -0.004159724,
+              -0.058231864,
+              -0.033032075,
+              0.0040235794,
+              -0.019985583,
+              -0.020122562,
+              0.055365406,
+              0.10250875,
+              -0.10799118,
+              -0.013780294,
+              -0.009652406,
+              0.015592658,
+              -0.031221472,
+              0.1329332,
+              0.15243866,
+              -0.022426173
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 3,
+          "total_tokens": 3
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/41e27b9b5d09.json

@@ -0,0 +1,42 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/completions",
+    "headers": {},
+    "body": {
+      "model": "llama3.2:3b-instruct-fp16",
+      "prompt": "Say completions",
+      "max_tokens": 20
+    },
+    "endpoint": "/v1/completions",
+    "model": "llama3.2:3b-instruct-fp16"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.completion.Completion",
+      "__data__": {
+        "id": "cmpl-271",
+        "choices": [
+          {
+            "finish_reason": "length",
+            "index": 0,
+            "logprobs": null,
+            "text": "You want me to respond with a completion, but you didn't specify what I should complete. Could"
+          }
+        ],
+        "created": 1756846620,
+        "model": "llama3.2:3b-instruct-fp16",
+        "object": "text_completion",
+        "system_fingerprint": "fp_ollama",
+        "usage": {
+          "completion_tokens": 20,
+          "prompt_tokens": 28,
+          "total_tokens": 48,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/4420515208a8.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "What is the secret string?"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.07473014,
+              0.08137506,
+              -0.06463602,
+              0.011821943,
+              -0.07454815,
+              0.021821007,
+              0.077573344,
+              0.012804661,
+              0.05853777,
+              -0.014141324,
+              0.053993534,
+              -0.026554074,
+              -0.018055506,
+              -0.060447972,
+              -0.019253474,
+              -0.006501444,
+              -0.047272332,
+              -0.048944764,
+              -0.090516366,
+              -0.06656194,
+              0.09287066,
+              0.02129739,
+              -0.013401809,
+              -0.006629013,
+              0.0079892,
+              0.016818035,
+              0.03971694,
+              0.021875564,
+              0.014873574,
+              -0.039426163,
+              0.025255844,
+              -0.036836684,
+              0.016627828,
+              0.008789532,
+              -0.053503897,
+              0.03616121,
+              -0.034633957,
+              -0.009877797,
+              0.064843215,
+              -0.01517806,
+              0.020897496,
+              -0.07135096,
+              -0.008519908,
+              0.05118655,
+              -0.062102985,
+              0.059486073,
+              -0.047937352,
+              0.07045817,
+              -0.024867272,
+              -0.010756205,
+              0.06538509,
+              -0.03693754,
+              -0.08240387,
+              0.08169191,
+              0.017090658,
+              0.012944557,
+              -0.047139525,
+              0.0025796075,
+              0.008701712,
+              0.099866174,
+              0.04969699,
+              -0.025922626,
+              -0.017354922,
+              0.03395182,
+              0.038391408,
+              -0.054247838,
+              0.008610521,
+              -0.04077977,
+              0.0265637,
+              -0.07186012,
+              -0.019953186,
+              -0.041191205,
+              -0.07246228,
+              0.00041248833,
+              0.018758524,
+              0.023036895,
+              0.01662864,
+              -0.06335885,
+              0.03495032,
+              0.050063577,
+              0.00043262896,
+              -0.06176693,
+              0.0062733325,
+              0.11142063,
+              0.0040838965,
+              0.085737824,
+              0.023284689,
+              0.05699812,
+              -0.03149832,
+              -0.013344509,
+              -0.045138564,
+              -0.117300816,
+              0.016063986,
+              -0.016894838,
+              -0.028934335,
+              0.03575864,
+              -0.05156192,
+              0.032958068,
+              -0.11266628,
+              0.06640015,
+              0.037839692,
+              0.022948038,
+              0.058071073,
+              -0.039643735,
+              -0.03247236,
+              0.017690921,
+              -0.005001274,
+              0.019046135,
+              0.07745316,
+              -0.020402163,
+              -0.020310633,
+              -0.009519755,
+              0.0031459313,
+              -0.0045639877,
+              -0.029116316,
+              0.033835515,
+              0.00050839526,
+              0.06419946,
+              0.010721198,
+              0.124151744,
+              -0.0053820186,
+              0.00491648,
+              -0.059696514,
+              0.029483523,
+              -0.13409872,
+              0.016187217,
+              -0.048092023,
+              -6.6084764e-33,
+              0.012305612,
+              0.060384244,
+              0.036461998,
+              -0.035974216,
+              -0.04197416,
+              0.012333701,
+              -0.084805995,
+              0.012502633,
+              0.02794982,
+              0.0861082,
+              -0.030791838,
+              -0.061355945,
+              -0.0009604986,
+              -0.0252044,
+              0.045444816,
+              -0.027590565,
+              -0.009594973,
+              0.006712001,
+              0.043692384,
+              -0.021483036,
+              0.003300438,
+              0.11860881,
+              0.047044385,
+              -0.1348901,
+              0.025469579,
+              -0.01029819,
+              0.0022393467,
+              -0.061863262,
+              0.10386513,
+              0.018658707,
+              -0.0017492755,
+              -0.051914047,
+              0.046442248,
+              0.03761067,
+              0.033752125,
+              0.006650237,
+              0.022015076,
+              -0.07834835,
+              -0.008209136,
+              0.027432231,
+              0.017393896,
+              -0.07524756,
+              0.006497012,
+              0.027272953,
+              0.0005804994,
+              -0.010941825,
+              -0.020050043,
+              -0.00012092298,
+              0.013705002,
+              0.004699541,
+              0.022770848,
+              0.015477994,
+              -0.0142482165,
+              -0.013953546,
+              0.015865315,
+              -0.023075614,
+              0.03379947,
+              -0.039221376,
+              -0.043229815,
+              0.02998769,
+              -0.01652291,
+              0.06981088,
+              0.04606923,
+              0.05332633,
+              -0.055300076,
+              0.02511626,
+              0.014049543,
+              -0.09398743,
+              0.03590562,
+              0.029452223,
+              -0.13200304,
+              -0.005059034,
+              -0.03784268,
+              -0.03180819,
+              -0.095502876,
+              -0.027853556,
+              0.0024331037,
+              -0.007881495,
+              0.058296,
+              -0.031999517,
+              -0.06077097,
+              -0.023381822,
+              -0.00048603877,
+              0.13765746,
+              -0.060579,
+              -0.008109843,
+              -0.034873307,
+              -0.1024547,
+              -0.009072849,
+              -0.018931676,
+              -0.0016711762,
+              -0.07710289,
+              -0.043332253,
+              -0.03619527,
+              0.03958017,
+              3.0217083e-33,
+              0.0050329794,
+              0.00016030145,
+              -0.063078895,
+              0.012225751,
+              0.10637338,
+              0.015972024,
+              0.006653195,
+              0.01880781,
+              -0.04708357,
+              0.045863643,
+              0.0076015075,
+              0.03243478,
+              0.032097474,
+              -0.020893326,
+              0.10697852,
+              0.0075498912,
+              0.036074348,
+              0.1462344,
+              0.03779065,
+              -0.043190572,
+              -0.02176097,
+              -0.009340132,
+              -0.06983617,
+              0.015578788,
+              0.021121953,
+              0.030661412,
+              0.08434581,
+              -0.09288574,
+              0.008169474,
+              0.078080945,
+              -0.081626564,
+              0.011895231,
+              0.017099649,
+              0.0040119104,
+              -0.14145434,
+              0.0040375097,
+              0.046316408,
+              0.008959473,
+              -0.0056506568,
+              -0.055587813,
+              0.028007837,
+              0.055937108,
+              0.062269785,
+              0.08602392,
+              -0.12157818,
+              0.021943888,
+              -0.0050934856,
+              0.029819332,
+              -0.012127162,
+              0.048801802,
+              0.06409215,
+              -0.041438665,
+              0.01809265,
+              -0.028214281,
+              -0.0213588,
+              0.05564267,
+              -0.1547868,
+              0.027465124,
+              0.018855799,
+              0.04327939,
+              0.011500479,
+              0.017364705,
+              -0.023216385,
+              0.051007293,
+              0.02946264,
+              0.012533944,
+              -0.04542834,
+              -0.002238765,
+              -0.05611544,
+              -0.0789272,
+              0.07960444,
+              -0.020431034,
+              -0.0762138,
+              0.011588508,
+              -0.035614885,
+              -0.04803985,
+              -0.06607436,
+              -0.057365946,
+              -0.040188126,
+              0.07176218,
+              0.03135825,
+              0.02303279,
+              -0.023997622,
+              0.023614945,
+              0.09607302,
+              -0.06843066,
+              0.014260722,
+              0.08802569,
+              -0.037736766,
+              0.029445928,
+              -0.028643936,
+              0.10217973,
+              -0.0660917,
+              0.022864237,
+              0.042151757,
+              -1.4814046e-08,
+              0.030838449,
+              0.043877687,
+              -0.0245681,
+              -0.09818859,
+              0.056659035,
+              0.0929652,
+              -0.010337853,
+              -0.0983916,
+              0.018008571,
+              -0.0131424805,
+              0.026400762,
+              0.008793538,
+              -0.05285605,
+              -0.042175982,
+              0.030133193,
+              0.01710666,
+              -0.06242493,
+              -0.018753909,
+              -0.015986755,
+              -0.018400662,
+              -0.026477808,
+              0.010281372,
+              -0.030476814,
+              -0.084556945,
+              -0.05402664,
+              0.010030052,
+              0.029531356,
+              0.13555466,
+              0.033426728,
+              0.12098221,
+              0.040777553,
+              0.008206964,
+              -0.018235989,
+              -0.0568263,
+              -0.1289943,
+              0.12416113,
+              -0.053454727,
+              -0.038151894,
+              0.030221034,
+              0.019807614,
+              0.047819767,
+              0.029434063,
+              0.0015704447,
+              0.0611775,
+              -0.05557245,
+              -0.030236417,
+              0.10799873,
+              -0.07073352,
+              -0.08215229,
+              0.004518122,
+              -0.015573616,
+              -0.013696145,
+              -0.0023438279,
+              0.026377691,
+              -0.015769389,
+              0.016251203,
+              -0.04062322,
+              -0.013962793,
+              -0.08309221,
+              0.031991288,
+              0.049991824,
+              -0.0038595141,
+              0.07031122,
+              0.0049263495
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 6,
+          "total_tokens": 6
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/44a1d9de0602.json

@@ -20,7 +20,7 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-987",
+        "id": "chatcmpl-507",
         "choices": [
           {
             "finish_reason": "length",
@@ -37,7 +37,7 @@
             }
           }
         ],
-        "created": 1755294921,
+        "created": 1756921150,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,

tests/integration/recordings/responses/44fb9cf5875f.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-07-31T17:59:42.166585642Z",
+        "created_at": "2025-09-03T17:41:49.581065Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 9490295253,
-        "load_duration": 42349084,
+        "total_duration": 2391571708,
+        "load_duration": 182022958,
         "prompt_eval_count": 20,
-        "prompt_eval_duration": 545470166,
+        "prompt_eval_duration": 74456583,
         "eval_count": 51,
-        "eval_duration": 8901928284,
+        "eval_duration": 2134471458,
         "response": "It seems like you're trying to test the system, but I'm not sure what specific functionality or feature you'd like to test. Could you please provide more context or clarify what you're looking for? I'll do my best to assist you!",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/48d2fb183a2a.json

@@ -67,15 +67,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-08-04T22:55:40.583477Z",
+        "created_at": "2025-09-03T17:36:40.283084Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 3928481500,
-        "load_duration": 151903250,
+        "total_duration": 2900042958,
+        "load_duration": 83372125,
         "prompt_eval_count": 259,
-        "prompt_eval_duration": 468000000,
+        "prompt_eval_duration": 352890750,
         "eval_count": 60,
-        "eval_duration": 3306000000,
+        "eval_duration": 2462885208,
         "response": "{\n  \"first_name\": \"Michael\",\n  \"last_name\": \"Jordan\",\n  \"year_of_birth\": 1963,\n  \"nba_stats\": {\n    \"year_for_draft\": 1984,\n    \"num_seasons_in_nba\": 15\n  }\n}",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/4ca6152a0eb8.json

@@ -0,0 +1,59 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Which planet has rings around it with a name starting with letter S?"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "oBUtaEp-62bZhn-9801a2718d0ed123",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "The planet with rings around it that starts with the letter S is Saturn. Saturn's ring system is one of the most prominent and well-known in our solar system.",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": []
+            },
+            "seed": 2387155844510162400
+          }
+        ],
+        "created": 1758039032,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 34,
+          "prompt_tokens": 49,
+          "total_tokens": 83,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/50340cd4d253.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:14:19.298378Z",
+        "created_at": "2025-09-03T17:38:01.239743Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 266786083,
-        "load_duration": 53820458,
+        "total_duration": 207264667,
+        "load_duration": 73437959,
         "prompt_eval_count": 216,
-        "prompt_eval_duration": 192000000,
+        "prompt_eval_duration": 121657333,
         "eval_count": 2,
-        "eval_duration": 17000000,
+        "eval_duration": 11348417,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/5370751803dc.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "Python is a high-level programming language with code readability and fewer lines than C++ or Java"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.07642644,
+              0.0213101,
+              -0.03612849,
+              -0.0012144424,
+              -0.048599217,
+              -0.13194773,
+              -0.084226094,
+              0.059389386,
+              -0.0617182,
+              -0.009323243,
+              -0.08099486,
+              0.055514984,
+              0.052610602,
+              0.026061919,
+              0.063071534,
+              -0.062316332,
+              -0.065115415,
+              -0.022351492,
+              0.017378356,
+              -0.11605584,
+              -0.036349725,
+              0.0404155,
+              -0.0325302,
+              -0.01770141,
+              0.05722761,
+              0.012393438,
+              -0.018529164,
+              -0.030017126,
+              0.002365914,
+              0.0066701965,
+              -0.08862459,
+              0.0779319,
+              0.03702611,
+              0.029523117,
+              -0.01977821,
+              0.05424799,
+              -0.00074063655,
+              -0.08949148,
+              -0.05312112,
+              -0.012703181,
+              -0.08622611,
+              0.07689996,
+              -0.038602136,
+              -0.011616902,
+              -0.03234132,
+              -0.0073969415,
+              -0.024779495,
+              -0.067999884,
+              -0.03039565,
+              -0.025974417,
+              -0.09690519,
+              0.009931951,
+              -0.05362519,
+              -0.09107193,
+              -0.009222061,
+              -0.008804084,
+              0.048185978,
+              -0.003329437,
+              -0.0058579347,
+              -0.13306528,
+              -0.09721703,
+              0.013474277,
+              0.047286008,
+              0.06279936,
+              -0.01582815,
+              -0.03771013,
+              -0.01651892,
+              0.029905442,
+              0.09326656,
+              -0.06746783,
+              -0.13385954,
+              -0.020873511,
+              -0.02586237,
+              0.11623731,
+              0.030632136,
+              -0.10494776,
+              0.03905967,
+              -0.010701787,
+              -0.0014734551,
+              0.020711906,
+              0.0017687598,
+              0.027797814,
+              -0.078500465,
+              0.10791581,
+              0.02910256,
+              -0.05398749,
+              0.030513834,
+              0.07001416,
+              -0.034323946,
+              0.00986597,
+              0.034644563,
+              -0.04232179,
+              0.065106474,
+              0.026648693,
+              -0.032122962,
+              0.07616709,
+              0.020026332,
+              -0.030642457,
+              -0.07188906,
+              0.027189687,
+              -0.018678213,
+              -0.05416582,
+              0.07488992,
+              0.017753933,
+              0.03386007,
+              0.02414506,
+              0.09077034,
+              -0.052096054,
+              0.040722203,
+              -0.018450806,
+              -0.012474094,
+              -0.06403705,
+              -0.023205942,
+              -0.061878704,
+              0.053436812,
+              0.047876816,
+              -0.010608645,
+              0.07852118,
+              0.03579911,
+              0.027097313,
+              0.022424318,
+              -0.004912598,
+              -0.02455264,
+              0.003700777,
+              0.00039888592,
+              -0.008842094,
+              0.009365857,
+              2.05052e-34,
+              -0.03236592,
+              -0.024301885,
+              0.027186498,
+              0.021633558,
+              0.06519107,
+              -0.019539308,
+              0.05306087,
+              0.007985293,
+              -0.03927361,
+              -0.020062907,
+              0.008070545,
+              0.02382429,
+              0.015006528,
+              0.1128094,
+              0.06113956,
+              -0.011911169,
+              0.016901307,
+              0.045509744,
+              0.0013988831,
+              0.00907712,
+              0.01314859,
+              -0.012022324,
+              0.027043821,
+              0.0071581583,
+              0.022573117,
+              -0.013721936,
+              -0.004378743,
+              -0.0007087661,
+              0.033585846,
+              0.011227843,
+              -0.05136015,
+              -0.0739591,
+              -0.03094639,
+              0.01957863,
+              -0.010360539,
+              -0.0029881562,
+              -0.00480912,
+              -0.10446798,
+              0.034694213,
+              -0.02424012,
+              -0.047155295,
+              0.035451673,
+              0.037169226,
+              -0.016986743,
+              0.0056092087,
+              0.05057555,
+              -0.008601115,
+              0.0060349177,
+              -0.12273999,
+              0.036871877,
+              -0.022267655,
+              -0.009739047,
+              0.075974636,
+              0.08902226,
+              0.01647873,
+              0.044345584,
+              0.06792565,
+              0.06456903,
+              -0.050189856,
+              -0.0016995457,
+              -0.00090498856,
+              0.09925942,
+              0.09253569,
+              -0.011321612,
+              0.050309792,
+              0.07697773,
+              0.0100068,
+              0.101032645,
+              0.03268899,
+              0.06433435,
+              -0.044524822,
+              0.03860177,
+              -0.019314477,
+              0.037440598,
+              -0.0017394378,
+              0.011816814,
+              0.011359969,
+              -0.1040215,
+              0.06984421,
+              0.01910163,
+              -0.028409261,
+              -0.013704911,
+              0.048502754,
+              -0.015429918,
+              -0.03423058,
+              -0.055616368,
+              0.005001686,
+              0.026054256,
+              -0.0007700968,
+              -0.0041726283,
+              -0.0640977,
+              -0.05985385,
+              0.0813829,
+              0.014288322,
+              -0.038147252,
+              -2.1576616e-33,
+              -0.027279941,
+              -0.034765568,
+              -0.02465107,
+              0.026859807,
+              -0.090699576,
+              -0.045698144,
+              0.013666582,
+              0.002109106,
+              0.054007426,
+              0.032838397,
+              -0.029939773,
+              -0.058843046,
+              0.09825693,
+              0.03251322,
+              0.109977886,
+              0.020682266,
+              -0.0958973,
+              0.0005566991,
+              0.0018037638,
+              0.017544486,
+              -0.06843023,
+              0.06435102,
+              -0.050149646,
+              -0.048880838,
+              -0.027535524,
+              -0.014993001,
+              -0.1210176,
+              -0.04412877,
+              -0.011025324,
+              0.058610573,
+              -0.007498303,
+              0.038722932,
+              -0.07025986,
+              0.030281536,
+              0.055707317,
+              -0.001162887,
+              0.01707519,
+              -0.042081844,
+              -0.016578361,
+              -0.025714336,
+              0.117893435,
+              0.04196084,
+              0.064787276,
+              0.046081997,
+              0.014950138,
+              0.030026693,
+              -0.039077066,
+              0.087156676,
+              -0.012328571,
+              -0.035646956,
+              -0.048145168,
+              0.041394625,
+              0.038984135,
+              -0.025188481,
+              -0.028836856,
+              -0.02917782,
+              0.029690607,
+              0.051454436,
+              -0.08629761,
+              -0.06921346,
+              -0.07273269,
+              -0.05952071,
+              0.0050034616,
+              0.025693603,
+              -0.022103382,
+              0.024972659,
+              -0.09724792,
+              0.0062089814,
+              -0.04963219,
+              -0.13054384,
+              0.124669954,
+              -0.01361085,
+              -0.022798477,
+              0.039057832,
+              -0.07550591,
+              0.049364913,
+              0.0007779102,
+              0.004692535,
+              -0.040757872,
+              0.06355995,
+              0.110190175,
+              0.02015945,
+              -0.048807338,
+              0.05842704,
+              -0.066375315,
+              0.026938869,
+              -0.062775925,
+              -0.014049011,
+              0.023343485,
+              0.02358394,
+              -0.002172394,
+              0.07766165,
+              0.031056313,
+              0.020171564,
+              -0.020073414,
+              -2.4317085e-08,
+              0.020261949,
+              -0.008623839,
+              0.0621209,
+              -0.008334477,
+              0.02526615,
+              0.08902315,
+              -0.007958188,
+              -0.018911751,
+              -0.035572145,
+              0.06189234,
+              -0.017249323,
+              -0.030186126,
+              -0.10225455,
+              -0.06522741,
+              -0.004033112,
+              0.10897627,
+              -0.02168822,
+              -0.053784374,
+              0.011841631,
+              0.052263785,
+              0.058334205,
+              0.0052479547,
+              -0.06017166,
+              0.08723854,
+              -0.08275336,
+              -0.040676847,
+              0.065786876,
+              0.028317772,
+              -0.012168614,
+              -0.07196286,
+              0.014588226,
+              -0.03231537,
+              0.0028357722,
+              0.03868031,
+              0.055439528,
+              -0.015238348,
+              0.05482384,
+              -0.025080629,
+              -0.033771332,
+              0.0030752022,
+              -0.037511814,
+              0.015122315,
+              0.02292684,
+              0.012024873,
+              0.03559873,
+              0.006865039,
+              -0.04049267,
+              -0.049685854,
+              -0.05455341,
+              -0.073071465,
+              -0.024902396,
+              -0.002133957,
+              -0.013212662,
+              -0.06657236,
+              0.023245512,
+              0.046919,
+              -0.13278763,
+              -0.011092663,
+              -0.023939205,
+              0.043182902,
+              0.024406029,
+              0.06922961,
+              0.15658055,
+              0.017658537
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 21,
+          "total_tokens": 21
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/545d86510a80.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.59711Z",
+          "created_at": "2025-09-03T17:42:32.625862Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.671294Z",
+          "created_at": "2025-09-03T17:42:32.668885Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.736161Z",
+          "created_at": "2025-09-03T17:42:32.710947Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.809857Z",
+          "created_at": "2025-09-03T17:42:32.752286Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.883599Z",
+          "created_at": "2025-09-03T17:42:32.793309Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.942471Z",
+          "created_at": "2025-09-03T17:42:32.834578Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:38.999844Z",
+          "created_at": "2025-09-03T17:42:32.876536Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:39.050862Z",
+          "created_at": "2025-09-03T17:42:32.918807Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:39.104589Z",
+          "created_at": "2025-09-03T17:42:32.960101Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:39.158301Z",
+          "created_at": "2025-09-03T17:42:33.00196Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:39.210985Z",
+          "created_at": "2025-09-03T17:42:33.043876Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:39.263525Z",
+          "created_at": "2025-09-03T17:42:33.08756Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,15 +238,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:39.314455Z",
+          "created_at": "2025-09-03T17:42:33.12966Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 914060542,
-          "load_duration": 63705209,
+          "total_duration": 648814958,
+          "load_duration": 75300875,
           "prompt_eval_count": 408,
-          "prompt_eval_duration": 95000000,
+          "prompt_eval_duration": 66740291,
           "eval_count": 13,
-          "eval_duration": 753000000,
+          "eval_duration": 505313125,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/554de3cd986f.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.40585Z",
+          "created_at": "2025-09-03T17:37:51.805591Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.455647Z",
+          "created_at": "2025-09-03T17:37:51.850067Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.509581Z",
+          "created_at": "2025-09-03T17:37:51.892443Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.56592Z",
+          "created_at": "2025-09-03T17:37:51.934364Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.616979Z",
+          "created_at": "2025-09-03T17:37:51.978382Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.671413Z",
+          "created_at": "2025-09-03T17:37:52.019332Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.725494Z",
+          "created_at": "2025-09-03T17:37:52.060708Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.779905Z",
+          "created_at": "2025-09-03T17:37:52.102717Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.829791Z",
+          "created_at": "2025-09-03T17:37:52.143996Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.880729Z",
+          "created_at": "2025-09-03T17:37:52.185479Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.93338Z",
+          "created_at": "2025-09-03T17:37:52.227562Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:04.981714Z",
+          "created_at": "2025-09-03T17:37:52.270178Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,7 +238,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.036068Z",
+          "created_at": "2025-09-03T17:37:52.31151Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -256,7 +256,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.088069Z",
+          "created_at": "2025-09-03T17:37:52.35278Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -274,7 +274,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.144485Z",
+          "created_at": "2025-09-03T17:37:52.393954Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -292,7 +292,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.203042Z",
+          "created_at": "2025-09-03T17:37:52.435238Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -310,7 +310,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.257133Z",
+          "created_at": "2025-09-03T17:37:52.476197Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -328,7 +328,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.311623Z",
+          "created_at": "2025-09-03T17:37:52.517914Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -346,15 +346,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:05.370124Z",
+          "created_at": "2025-09-03T17:37:52.55904Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1532801458,
-          "load_duration": 213911041,
+          "total_duration": 971882292,
+          "load_duration": 116634209,
           "prompt_eval_count": 376,
-          "prompt_eval_duration": 350000000,
+          "prompt_eval_duration": 99382958,
           "eval_count": 19,
-          "eval_duration": 967000000,
+          "eval_duration": 755260750,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/561746e1c8de.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:49.18651486Z",
+          "created_at": "2025-09-03T17:36:20.465701Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:49.370611348Z",
+          "created_at": "2025-09-03T17:36:20.507671Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:49.557000029Z",
+          "created_at": "2025-09-03T17:36:20.549443Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:49.746777116Z",
+          "created_at": "2025-09-03T17:36:20.590803Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:49.942233333Z",
+          "created_at": "2025-09-03T17:36:20.631683Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:50.126788846Z",
+          "created_at": "2025-09-03T17:36:20.672443Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:50.311346131Z",
+          "created_at": "2025-09-03T17:36:20.713329Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:50.501507173Z",
+          "created_at": "2025-09-03T17:36:20.754254Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:50.692296777Z",
+          "created_at": "2025-09-03T17:36:20.795119Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:50.878846539Z",
+          "created_at": "2025-09-03T17:36:20.836145Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,15 +201,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-15T20:24:51.063200561Z",
+          "created_at": "2025-09-03T17:36:20.877784Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 33982453650,
-          "load_duration": 2909001805,
+          "total_duration": 612057417,
+          "load_duration": 97443583,
           "prompt_eval_count": 341,
-          "prompt_eval_duration": 29194357307,
+          "prompt_eval_duration": 100914750,
           "eval_count": 11,
-          "eval_duration": 1878247732,
+          "eval_duration": 413024250,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/563b994bb7d1.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-08-04T22:55:13.25248Z",
+        "created_at": "2025-09-03T17:36:19.594923Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 1344654917,
-        "load_duration": 200585375,
+        "total_duration": 988472417,
+        "load_duration": 117976625,
         "prompt_eval_count": 326,
-        "prompt_eval_duration": 564000000,
+        "prompt_eval_duration": 451625542,
         "eval_count": 11,
-        "eval_duration": 578000000,
+        "eval_duration": 418313417,
         "response": "[get_weather(location=\"San Francisco, CA\")]",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/565b1072cb9d.json

@@ -0,0 +1,46 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "prompt": "Respond to this question and explain your answer. Complete the sentence using one word: Roses are red, violets are ",
+      "stream": false,
+      "extra_body": {}
+    },
+    "endpoint": "/v1/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.completion.Completion",
+      "__data__": {
+        "id": "oBUswCe-62bZhn-98019f663cac0f68",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "text": " _______________________. \n\n## Step 1: Identify the traditional completion of the sentence.\nThe traditional completion of the sentence \"Roses are red, violets are...\" is based on a well-known poem.\n\n## Step 2: Recall the poem.\nThe poem states, \"Roses are red, violets are blue...\"\n\n## Step 3: Determine the word that completes the sentence.\nBased on the poem, the word that completes the sentence is \"blue\".\n\nThe final answer is: $\\boxed{blue}$",
+            "seed": 4892505926413923000
+          }
+        ],
+        "created": 1758038908,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+        "object": "text.completion",
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 106,
+          "prompt_tokens": 25,
+          "total_tokens": 131,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/57b67d1b1a36.json

@@ -0,0 +1,71 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://shan-mfbb618r-eastus2.cognitiveservices.azure.com/openai/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-5-mini",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Which planet has rings around it with a name starting with letter S?"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-5-mini"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "chatcmpl-CECIkT5cbqFazpungtewksVePcUNa",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "Saturn. It's the planet famous for its prominent ring system made of ice and rock.",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": [],
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            },
+            "content_filter_results": {}
+          }
+        ],
+        "created": 1757499914,
+        "model": "gpt-5-mini-2025-08-07",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 156,
+          "prompt_tokens": 20,
+          "total_tokens": 176,
+          "completion_tokens_details": {
+            "accepted_prediction_tokens": 0,
+            "audio_tokens": 0,
+            "reasoning_tokens": 128,
+            "rejected_prediction_tokens": 0
+          },
+          "prompt_tokens_details": {
+            "audio_tokens": 0,
+            "cached_tokens": 0
+          }
+        },
+        "prompt_filter_results": [
+          {
+            "prompt_index": 0,
+            "content_filter_results": {}
+          }
+        ]
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/5f5d16afadb4.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.354888Z",
+          "created_at": "2025-09-03T17:36:19.808372Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.427569Z",
+          "created_at": "2025-09-03T17:36:19.84991Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.486244Z",
+          "created_at": "2025-09-03T17:36:19.892111Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.540455Z",
+          "created_at": "2025-09-03T17:36:19.933857Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.594439Z",
+          "created_at": "2025-09-03T17:36:19.975148Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.649837Z",
+          "created_at": "2025-09-03T17:36:20.016641Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.703358Z",
+          "created_at": "2025-09-03T17:36:20.058229Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.7553Z",
+          "created_at": "2025-09-03T17:36:20.100222Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.807251Z",
+          "created_at": "2025-09-03T17:36:20.143456Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.857952Z",
+          "created_at": "2025-09-03T17:36:20.184657Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,15 +201,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:13.918522Z",
+          "created_at": "2025-09-03T17:36:20.226017Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 647785042,
-          "load_duration": 26355584,
+          "total_duration": 598395375,
+          "load_duration": 129432167,
           "prompt_eval_count": 326,
-          "prompt_eval_duration": 55000000,
+          "prompt_eval_duration": 50057334,
           "eval_count": 11,
-          "eval_duration": 557000000,
+          "eval_duration": 418284791,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/62aa454ea5f9.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "What inspires neural networks?"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.08566708,
+              -0.09559047,
+              0.044014607,
+              -0.015974598,
+              0.029406257,
+              0.07229597,
+              -0.010901963,
+              -0.023829829,
+              0.07381301,
+              -0.05698464,
+              -0.033780586,
+              0.051200844,
+              0.0050912783,
+              0.014317088,
+              -0.07878143,
+              -0.012908666,
+              -0.041628323,
+              0.06881713,
+              -0.10783476,
+              -0.04042705,
+              0.026262026,
+              -0.0019893218,
+              -0.011008084,
+              -0.0019646112,
+              0.004033132,
+              0.08881656,
+              0.014049165,
+              -0.018416086,
+              0.032621212,
+              -0.034692146,
+              0.07614942,
+              -0.014122101,
+              -0.024901746,
+              0.03755059,
+              -0.10197354,
+              0.054705318,
+              -0.022539826,
+              0.024209768,
+              0.011698194,
+              -0.008956377,
+              -0.050146304,
+              0.0026327297,
+              0.055942897,
+              0.009974366,
+              0.12796965,
+              -0.025006283,
+              0.024338534,
+              -0.024487961,
+              -0.0022703854,
+              -0.024687177,
+              -0.10482094,
+              -0.05994297,
+              -0.055200897,
+              0.0152664175,
+              0.03496896,
+              0.052624088,
+              -0.0006445885,
+              0.06637695,
+              -0.031790398,
+              -0.007308742,
+              -0.0050764186,
+              -0.042508755,
+              -0.04089097,
+              0.020062948,
+              0.038683955,
+              0.022463562,
+              -0.02866933,
+              0.053370677,
+              0.022435635,
+              0.01934692,
+              0.12264713,
+              0.023911418,
+              -0.037264284,
+              0.0059156846,
+              0.05235448,
+              0.054004095,
+              0.08022169,
+              -0.010992806,
+              0.029295033,
+              -0.0672064,
+              -0.00021147476,
+              -0.050584126,
+              -0.0095251575,
+              0.04616498,
+              0.078677796,
+              0.01416309,
+              -0.033226117,
+              0.0018380182,
+              -0.06667651,
+              -0.020977372,
+              -0.017116925,
+              -0.04396714,
+              -0.05969979,
+              -0.07344942,
+              -0.03985366,
+              -0.030863814,
+              -0.019918729,
+              -0.1075161,
+              -0.026654154,
+              0.0689854,
+              -0.0049292273,
+              0.026645623,
+              0.018879393,
+              0.022113768,
+              0.064208575,
+              -0.053153764,
+              0.06160797,
+              0.014026719,
+              0.11772326,
+              -0.051769163,
+              -0.07634968,
+              0.03090975,
+              -0.038558383,
+              -0.025260162,
+              0.039262023,
+              -0.061449137,
+              0.008389126,
+              0.016175874,
+              0.032293033,
+              0.06679397,
+              -0.06503257,
+              0.014676881,
+              -0.038542666,
+              0.018718671,
+              -0.030111106,
+              -0.028481327,
+              -0.14707623,
+              -3.455443e-33,
+              -0.048577547,
+              -0.024983348,
+              0.071679614,
+              0.035652317,
+              0.07931413,
+              -0.07811974,
+              0.023085583,
+              -0.047467884,
+              0.08872273,
+              -0.0010074769,
+              -0.11320135,
+              0.091322996,
+              0.023978539,
+              0.11368158,
+              0.042203873,
+              -0.05773289,
+              -0.074543044,
+              -0.0021036167,
+              -0.051522236,
+              -0.050925426,
+              -0.0016557347,
+              0.030671587,
+              0.045119714,
+              -0.03974729,
+              -0.05871358,
+              -0.030611658,
+              0.0017253247,
+              0.009114429,
+              -0.013763352,
+              0.023424039,
+              0.0017495834,
+              0.046633217,
+              -0.07230643,
+              -0.027882291,
+              0.016182518,
+              0.044456217,
+              -0.004326421,
+              -0.061798126,
+              0.0697968,
+              0.031249145,
+              -0.013697079,
+              -0.007417679,
+              0.031665757,
+              -0.02367961,
+              0.07153089,
+              0.023938214,
+              0.009729952,
+              0.0071919435,
+              -0.03235391,
+              -0.04955071,
+              -0.050248373,
+              0.02151118,
+              0.015327139,
+              -0.0674203,
+              0.06544387,
+              -0.025547959,
+              0.03207046,
+              0.02038825,
+              0.0112230005,
+              0.00019493286,
+              -0.023462659,
+              -0.004949742,
+              -0.014066955,
+              0.0014178518,
+              0.059315395,
+              0.039931085,
+              -0.032498423,
+              -0.023698896,
+              0.05445033,
+              0.064231694,
+              -0.034013335,
+              0.08745776,
+              -0.080473825,
+              -0.090545714,
+              -0.065398656,
+              -8.2386265e-05,
+              -0.021441188,
+              -0.0684535,
+              -0.029121745,
+              0.034134887,
+              -0.07799698,
+              -0.05388711,
+              -0.035591345,
+              0.044826802,
+              -0.040090464,
+              0.07972004,
+              0.026058797,
+              -0.08184859,
+              0.0018106091,
+              -0.027676936,
+              -0.04312832,
+              -0.042090744,
+              0.08336437,
+              -0.049453646,
+              -0.0902778,
+              2.6716498e-33,
+              -0.091911495,
+              0.02641473,
+              -0.07022486,
+              0.075562105,
+              0.03900905,
+              0.027913846,
+              -0.05444872,
+              -0.036666486,
+              -0.048225258,
+              0.07551892,
+              0.046452336,
+              0.025874302,
+              0.052248206,
+              -0.00018527219,
+              0.010575236,
+              -0.040591337,
+              -0.028484622,
+              -0.020559357,
+              0.08882296,
+              -0.06755767,
+              0.04941752,
+              0.13231009,
+              -0.06998129,
+              -0.040112328,
+              0.044030365,
+              0.034218542,
+              -0.08650528,
+              0.05746921,
+              -0.0075130556,
+              0.049070083,
+              -0.0148686,
+              -0.018103259,
+              -0.020280316,
+              0.038828347,
+              0.022253176,
+              0.13486238,
+              0.06899369,
+              -0.002589861,
+              -0.016430879,
+              0.0033818923,
+              0.017275693,
+              0.013614936,
+              0.044220798,
+              0.049155377,
+              -0.008259856,
+              -0.046575654,
+              -0.043921605,
+              0.04156687,
+              -0.035468902,
+              0.042837795,
+              0.03131579,
+              0.017961076,
+              -0.026213305,
+              -0.05458616,
+              -0.04259084,
+              -0.004110002,
+              0.029035388,
+              0.0010451805,
+              0.09044077,
+              0.014110149,
+              -0.068820216,
+              -0.07098938,
+              0.020328037,
+              0.00433692,
+              -0.046977337,
+              0.016492791,
+              -0.028396707,
+              0.104340956,
+              0.002814702,
+              -0.08339559,
+              0.037326302,
+              0.058929898,
+              0.0376423,
+              0.09580634,
+              -0.12376848,
+              -0.054060236,
+              -0.014485116,
+              0.0013106487,
+              -0.04537336,
+              -0.0899294,
+              0.001730278,
+              -0.05520831,
+              0.000568523,
+              0.00053380145,
+              0.07856981,
+              0.104590714,
+              0.00355283,
+              0.008365939,
+              0.04291482,
+              0.010064388,
+              0.025177509,
+              0.05732803,
+              -0.023061136,
+              0.054399785,
+              -0.049828697,
+              -1.3290186e-08,
+              -0.0539168,
+              0.08074109,
+              0.03397028,
+              0.024365881,
+              0.0906225,
+              -0.07162824,
+              0.07550329,
+              0.017278913,
+              -0.061226364,
+              -0.03298407,
+              0.07829606,
+              0.03967995,
+              -0.036696997,
+              0.02665964,
+              0.1000655,
+              -0.014426734,
+              0.020708792,
+              -0.039230846,
+              0.0085029,
+              -0.0012509917,
+              0.06740856,
+              0.013992665,
+              -0.054007422,
+              -0.016785627,
+              0.07651403,
+              -0.035508703,
+              -0.050085396,
+              0.08382383,
+              -0.009957674,
+              0.08140875,
+              0.019287178,
+              0.049911316,
+              0.0022236605,
+              -0.07807412,
+              0.019454133,
+              0.111560374,
+              -0.01269702,
+              -0.06466137,
+              -0.09346588,
+              -0.050038446,
+              -0.042178612,
+              0.0599713,
+              0.034831088,
+              -0.014957726,
+              0.014484159,
+              -0.022619838,
+              0.06916277,
+              -0.088544875,
+              0.021478733,
+              0.01378541,
+              -0.0075770007,
+              0.027888266,
+              0.015526889,
+              0.0052174823,
+              0.010616002,
+              -0.022908956,
+              -0.02535865,
+              -0.04139556,
+              -0.08375561,
+              0.092626974,
+              0.051755503,
+              0.09296614,
+              0.011223383,
+              -0.016759252
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 6,
+          "total_tokens": 6
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/6730dcde0b73.json

@@ -0,0 +1,756 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello, world!"
+        }
+      ],
+      "stream": true
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": "Hello",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 9906
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": "Hello",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": "!",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": "!",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " It",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 1102
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " It",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": "'s",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 596
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": "'s",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " nice",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 6555
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " nice",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " to",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 311
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " to",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " meet",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 3449
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " meet",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " you",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 499
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " you",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": ".",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 13
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": ".",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " Is",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 2209
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " Is",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " there",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 1070
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " there",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " something",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 2555
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " something",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " I",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 358
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " I",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " can",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 649
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " can",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " help",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 1520
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " help",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " you",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 499
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " you",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " with",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 449
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " with",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " or",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 477
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " or",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " would",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 1053
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " would",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " you",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 499
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " you",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " like",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 1093
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " like",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " to",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 311
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " to",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": " chat",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 6369
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": " chat",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": "?",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 30
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null,
+              "text": "?",
+              "seed": null
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtTzC-62bZhn-9801a1ee1bea25d8",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 128009
+              },
+              "finish_reason": "stop",
+              "index": 0,
+              "logprobs": null,
+              "text": "",
+              "seed": 16158686754257986000
+            }
+          ],
+          "created": 1758039011,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": {
+            "completion_tokens": 25,
+            "prompt_tokens": 39,
+            "total_tokens": 64,
+            "completion_tokens_details": null,
+            "prompt_tokens_details": null,
+            "cached_tokens": 0
+          }
+        }
+      }
+    ],
+    "is_streaming": true
+  }
+}

tests/integration/recordings/responses/6857b19d3f0a.json

@@ -0,0 +1,87 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "messages": [
+        {
+          "role": "user",
+          "content": "What's the weather in Tokyo? Use the get_weather function to get the weather."
+        }
+      ],
+      "stream": false,
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "get_weather",
+            "description": "Get the weather in a given city",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "city": {
+                  "type": "string",
+                  "description": "The city to get the weather for"
+                }
+              }
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "oBUth9w-62bZhn-9801a3026bd20c8a",
+        "choices": [
+          {
+            "finish_reason": "tool_calls",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": null,
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": [
+                {
+                  "id": "call_8prwkicthj6bjfqa9ye64y2b",
+                  "function": {
+                    "arguments": "{\"city\":\"Tokyo\"}",
+                    "name": "get_weather"
+                  },
+                  "type": "function",
+                  "index": 0
+                }
+              ]
+            },
+            "seed": 977986247412336500
+          }
+        ],
+        "created": 1758039055,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 24,
+          "prompt_tokens": 193,
+          "total_tokens": 217,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/6906a6e71988.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:14:18.886381Z",
+        "created_at": "2025-09-03T17:38:00.98692Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 488566500,
-        "load_duration": 113477291,
+        "total_duration": 332473583,
+        "load_duration": 90611333,
         "prompt_eval_count": 317,
-        "prompt_eval_duration": 361000000,
+        "prompt_eval_duration": 229691000,
         "eval_count": 2,
-        "eval_duration": 12000000,
+        "eval_duration": 11571291,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/6c4e2e207e8a.json

@@ -1,54 +1,57 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/completions",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
     "headers": {},
     "body": {
-      "model": "llama3.2:3b-instruct-fp16",
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
       "messages": [
         {
           "role": "user",
-          "content": "Test trace openai 1"
+          "content": "Which planet do humans live on?"
         }
       ],
       "stream": false
     },
-    "endpoint": "/v1/completions",
-    "model": "llama3.2:3b-instruct-fp16"
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
   },
   "response": {
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-434",
+        "id": "oBUtMpf-62bZhn-9801a16bc8d642d3",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I don't have information on testing \"OpenAI\" as a product has not been released.",
+              "content": "Humans live on Earth.",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
               "audio": null,
               "function_call": null,
-              "tool_calls": null
-            }
+              "tool_calls": []
+            },
+            "seed": 14150443913665712000
           }
         ],
-        "created": 1754003706,
-        "model": "llama3.2:3b-instruct-fp16",
+        "created": 1758038990,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
         "object": "chat.completion",
         "service_tier": null,
-        "system_fingerprint": "fp_ollama",
+        "system_fingerprint": null,
         "usage": {
-          "completion_tokens": 20,
-          "prompt_tokens": 31,
-          "total_tokens": 51,
+          "completion_tokens": 6,
+          "prompt_tokens": 42,
+          "total_tokens": 48,
           "completion_tokens_details": null,
-          "prompt_tokens_details": null
-        }
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
       }
     },
     "is_streaming": false

tests/integration/recordings/responses/6cc063bbd7d3.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:55.9885Z",
+          "created_at": "2025-09-03T17:42:17.402486Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.054143Z",
+          "created_at": "2025-09-03T17:42:17.444334Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.117658Z",
+          "created_at": "2025-09-03T17:42:17.484625Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.179422Z",
+          "created_at": "2025-09-03T17:42:17.525063Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.240328Z",
+          "created_at": "2025-09-03T17:42:17.565015Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.295992Z",
+          "created_at": "2025-09-03T17:42:17.60499Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.355683Z",
+          "created_at": "2025-09-03T17:42:17.64509Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.412176Z",
+          "created_at": "2025-09-03T17:42:17.685566Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.466952Z",
+          "created_at": "2025-09-03T17:42:17.725855Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.517222Z",
+          "created_at": "2025-09-03T17:42:17.766056Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,7 +201,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.570491Z",
+          "created_at": "2025-09-03T17:42:17.806415Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -219,7 +219,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.623189Z",
+          "created_at": "2025-09-03T17:42:17.847273Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -237,7 +237,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.679221Z",
+          "created_at": "2025-09-03T17:42:17.888576Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -255,7 +255,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.731373Z",
+          "created_at": "2025-09-03T17:42:17.928952Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -273,7 +273,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.781364Z",
+          "created_at": "2025-09-03T17:42:17.969744Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -291,7 +291,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.831951Z",
+          "created_at": "2025-09-03T17:42:18.010869Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -309,7 +309,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.888381Z",
+          "created_at": "2025-09-03T17:42:18.051109Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -327,7 +327,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.943539Z",
+          "created_at": "2025-09-03T17:42:18.093266Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -345,7 +345,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:56.997422Z",
+          "created_at": "2025-09-03T17:42:18.135749Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -363,15 +363,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-04T22:55:57.056259Z",
+          "created_at": "2025-09-03T17:42:18.176649Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1289815458,
-          "load_duration": 119745583,
+          "total_duration": 907420000,
+          "load_duration": 66756750,
           "prompt_eval_count": 26,
-          "prompt_eval_duration": 98000000,
+          "prompt_eval_duration": 62900875,
           "eval_count": 20,
-          "eval_duration": 1071000000,
+          "eval_duration": 777306958,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/6d35c91287e2.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.362667Z",
+          "created_at": "2025-09-03T17:38:03.549266Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.427435Z",
+          "created_at": "2025-09-03T17:38:03.592203Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.484198Z",
+          "created_at": "2025-09-03T17:38:03.63417Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.537031Z",
+          "created_at": "2025-09-03T17:38:03.677268Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.591198Z",
+          "created_at": "2025-09-03T17:38:03.719768Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.643336Z",
+          "created_at": "2025-09-03T17:38:03.762204Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.698589Z",
+          "created_at": "2025-09-03T17:38:03.80404Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.752904Z",
+          "created_at": "2025-09-03T17:38:03.845678Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.804Z",
+          "created_at": "2025-09-03T17:38:03.887086Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.855633Z",
+          "created_at": "2025-09-03T17:38:03.928422Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.906918Z",
+          "created_at": "2025-09-03T17:38:03.969641Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:22.958729Z",
+          "created_at": "2025-09-03T17:38:04.011212Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,15 +238,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:23.011279Z",
+          "created_at": "2025-09-03T17:38:04.052626Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 793500292,
-          "load_duration": 55339750,
+          "total_duration": 731936583,
+          "load_duration": 147334791,
           "prompt_eval_count": 417,
-          "prompt_eval_duration": 83000000,
+          "prompt_eval_duration": 79443792,
           "eval_count": 13,
-          "eval_duration": 653000000,
+          "eval_duration": 504352750,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/6f96090aa955.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -21,7 +21,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -36,7 +36,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -47,7 +47,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -62,7 +62,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -73,11 +73,11 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
-                "content": " Welcome",
+                "content": " It",
                 "function_call": null,
                 "refusal": null,
                 "role": "assistant",
@@ -88,7 +88,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -99,7 +99,59 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
+          "choices": [
+            {
+              "delta": {
+                "content": "'s",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 1756921359,
+          "model": "llama3.2:3b-instruct-fp16",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": "fp_ollama",
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-698",
+          "choices": [
+            {
+              "delta": {
+                "content": " nice",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 1756921359,
+          "model": "llama3.2:3b-instruct-fp16",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": "fp_ollama",
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -114,7 +166,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -125,11 +177,11 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
-                "content": " our",
+                "content": " meet",
                 "function_call": null,
                 "refusal": null,
                 "role": "assistant",
@@ -140,7 +192,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -151,11 +203,11 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
-                "content": " conversation",
+                "content": " you",
                 "function_call": null,
                 "refusal": null,
                 "role": "assistant",
@@ -166,7 +218,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -177,7 +229,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -192,7 +244,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081849,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -203,7 +255,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -218,7 +270,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -229,7 +281,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -244,7 +296,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -255,7 +307,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -270,7 +322,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -281,7 +333,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -296,7 +348,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -307,7 +359,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -322,7 +374,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -333,7 +385,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -348,7 +400,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -359,7 +411,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -374,7 +426,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -385,7 +437,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -400,7 +452,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -411,33 +463,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
-          "choices": [
-            {
-              "delta": {
-                "content": ",",
-                "function_call": null,
-                "refusal": null,
-                "role": "assistant",
-                "tool_calls": null
-              },
-              "finish_reason": null,
-              "index": 0,
-              "logprobs": null
-            }
-          ],
-          "created": 1754081850,
-          "model": "llama3.2:3b-instruct-fp16",
-          "object": "chat.completion.chunk",
-          "service_tier": null,
-          "system_fingerprint": "fp_ollama",
-          "usage": null
-        }
-      },
-      {
-        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
-        "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -452,7 +478,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -463,7 +489,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -478,7 +504,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921359,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -489,7 +515,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -504,7 +530,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921360,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -515,7 +541,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -530,7 +556,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921360,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -541,7 +567,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -556,7 +582,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921360,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -567,7 +593,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -582,7 +608,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921360,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -593,7 +619,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -608,7 +634,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921360,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,
@@ -619,7 +645,7 @@
       {
         "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
         "__data__": {
-          "id": "chatcmpl-333",
+          "id": "chatcmpl-698",
           "choices": [
             {
               "delta": {
@@ -634,7 +660,7 @@
               "logprobs": null
             }
           ],
-          "created": 1754081850,
+          "created": 1756921360,
           "model": "llama3.2:3b-instruct-fp16",
           "object": "chat.completion.chunk",
           "service_tier": null,

tests/integration/recordings/responses/6fbea1abca7c.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.337763Z",
+          "created_at": "2025-09-03T17:38:01.89965Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.394358Z",
+          "created_at": "2025-09-03T17:38:01.941253Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.451349Z",
+          "created_at": "2025-09-03T17:38:01.982621Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.504443Z",
+          "created_at": "2025-09-03T17:38:02.024144Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.555779Z",
+          "created_at": "2025-09-03T17:38:02.065495Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.607807Z",
+          "created_at": "2025-09-03T17:38:02.107529Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.660627Z",
+          "created_at": "2025-09-03T17:38:02.149217Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.711562Z",
+          "created_at": "2025-09-03T17:38:02.190357Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.761822Z",
+          "created_at": "2025-09-03T17:38:02.231501Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.81712Z",
+          "created_at": "2025-09-03T17:38:02.272546Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.868755Z",
+          "created_at": "2025-09-03T17:38:02.313561Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.921049Z",
+          "created_at": "2025-09-03T17:38:02.354563Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,7 +238,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:20.973584Z",
+          "created_at": "2025-09-03T17:38:02.395585Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -256,7 +256,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:21.030707Z",
+          "created_at": "2025-09-03T17:38:02.436854Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -274,7 +274,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:21.082015Z",
+          "created_at": "2025-09-03T17:38:02.47814Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -292,7 +292,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:21.132945Z",
+          "created_at": "2025-09-03T17:38:02.519661Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -310,7 +310,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:21.187452Z",
+          "created_at": "2025-09-03T17:38:02.561119Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -328,7 +328,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:21.239827Z",
+          "created_at": "2025-09-03T17:38:02.602821Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -346,15 +346,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:21.294154Z",
+          "created_at": "2025-09-03T17:38:02.644633Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1929211666,
-          "load_duration": 61298666,
+          "total_duration": 1375629459,
+          "load_duration": 94090250,
           "prompt_eval_count": 386,
-          "prompt_eval_duration": 908000000,
+          "prompt_eval_duration": 535119167,
           "eval_count": 19,
-          "eval_duration": 959000000,
+          "eval_duration": 745684041,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/70adef2c30c4.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-08-04T22:55:55.720345Z",
+        "created_at": "2025-09-03T17:42:17.227488Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 3865701084,
-        "load_duration": 52435459,
+        "total_duration": 3003964916,
+        "load_duration": 111221916,
         "prompt_eval_count": 30,
-        "prompt_eval_duration": 99000000,
+        "prompt_eval_duration": 72578583,
         "eval_count": 70,
-        "eval_duration": 3712000000,
+        "eval_duration": 2819555375,
         "response": "The answer is Saturn! Saturn's ring system is one of the most iconic and well-known in our solar system. The rings are made up of ice particles, rock debris, and dust that orbit around the planet due to its gravitational pull.\n\nWould you like to know more about Saturn's rings or is there something else I can help you with?",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/72c1126ff2f9.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "artificial intelligence"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.024330618,
+              0.016706783,
+              0.037677176,
+              -0.00915746,
+              -0.030534461,
+              -0.017140884,
+              0.074272,
+              0.0456916,
+              -0.009377196,
+              0.009883053,
+              -0.0056895507,
+              0.007668296,
+              0.039537333,
+              0.015226257,
+              -0.083189555,
+              0.019439526,
+              -0.022046678,
+              -0.033254813,
+              -0.18105465,
+              -0.13025087,
+              -0.0022671346,
+              0.013451522,
+              -0.024325468,
+              -0.0370128,
+              0.0020083552,
+              0.08566712,
+              0.0047639925,
+              -0.0033431018,
+              -0.006082307,
+              -0.11575565,
+              0.06682902,
+              -0.018777572,
+              0.08786827,
+              -0.0074177794,
+              -0.093573004,
+              0.06146399,
+              -0.08110609,
+              0.012222862,
+              0.03971064,
+              -0.0026197461,
+              -0.04657111,
+              -0.08183902,
+              0.03959615,
+              0.015451151,
+              0.04370617,
+              0.103643835,
+              -0.058421485,
+              0.036699355,
+              -0.052699573,
+              0.040590122,
+              -0.12578927,
+              0.006500531,
+              -0.03583627,
+              -0.010050973,
+              -0.023851713,
+              0.045972254,
+              0.014605586,
+              0.019414552,
+              0.028465148,
+              -0.055030964,
+              0.024210233,
+              -0.052867457,
+              0.015230711,
+              -0.0043921247,
+              0.092372045,
+              0.033849865,
+              -0.04737281,
+              0.03204496,
+              0.001322036,
+              -0.051211488,
+              0.025862284,
+              0.08155327,
+              0.04092595,
+              0.019154705,
+              0.056453932,
+              -0.052758913,
+              0.030533386,
+              -0.01663434,
+              0.07877244,
+              -0.054262977,
+              -0.042149354,
+              -0.045443602,
+              -0.052689902,
+              0.11225497,
+              0.01989102,
+              -0.042375352,
+              -0.01168115,
+              0.024315914,
+              0.01915792,
+              -0.016550383,
+              -0.01030883,
+              -0.08545277,
+              0.023834355,
+              -0.042181373,
+              -0.02503509,
+              0.062114798,
+              -0.0045557353,
+              -0.15369569,
+              0.001106691,
+              0.19423288,
+              -0.0338511,
+              0.026152972,
+              -0.02032091,
+              0.0012884078,
+              -0.0010269672,
+              -0.02411262,
+              0.017495485,
+              -0.009808713,
+              0.07037937,
+              -0.13769862,
+              -0.11118059,
+              -0.01736481,
+              0.06603106,
+              -0.05188892,
+              0.0019610007,
+              0.014606686,
+              0.060775463,
+              0.096280165,
+              0.013551965,
+              0.019343173,
+              -0.00010512453,
+              -0.026652312,
+              -0.009341819,
+              0.07083247,
+              -0.0034617546,
+              -0.062412772,
+              -0.044611085,
+              -8.796679e-34,
+              -0.111884,
+              -0.04256611,
+              0.027425196,
+              0.06574074,
+              0.002830377,
+              -0.044104468,
+              0.005238822,
+              -0.036899913,
+              -0.015583552,
+              0.0206543,
+              -0.059225976,
+              0.007236511,
+              -0.028716031,
+              0.040467348,
+              0.13387093,
+              0.006795838,
+              -0.01636956,
+              0.082198486,
+              -0.02261007,
+              -0.03641293,
+              0.06524453,
+              0.021011814,
+              -0.005472363,
+              -0.038433436,
+              0.001462021,
+              0.0073671984,
+              0.016773427,
+              -0.062663026,
+              0.035388503,
+              -0.014395795,
+              0.027888605,
+              0.0837546,
+              -0.027772024,
+              -0.0036210797,
+              0.03903557,
+              -0.026879627,
+              -0.018737236,
+              0.019059159,
+              0.06522148,
+              0.0070414003,
+              0.004749159,
+              -0.0030224407,
+              0.040062208,
+              0.028016094,
+              -0.004660955,
+              0.012264517,
+              0.08708117,
+              -0.0070171114,
+              -0.03749808,
+              0.011326775,
+              0.015419708,
+              0.013775354,
+              0.017958472,
+              -0.009817919,
+              0.09011542,
+              0.05170552,
+              -0.034259036,
+              0.0043903207,
+              -0.01884889,
+              -0.031481344,
+              0.08216297,
+              0.016875258,
+              -0.022163702,
+              0.06844141,
+              0.01581623,
+              0.020322658,
+              0.0063856863,
+              0.016461994,
+              0.12718283,
+              0.014996434,
+              -0.010813858,
+              0.0017669421,
+              0.03166716,
+              -0.044353984,
+              -0.05225622,
+              0.022843942,
+              0.050988898,
+              -0.018916955,
+              0.0027930918,
+              -0.033645593,
+              -0.13571611,
+              -0.027015164,
+              -0.035672266,
+              -0.033537813,
+              0.047864296,
+              -0.0054381513,
+              0.021346755,
+              -0.040034927,
+              0.019374551,
+              0.012011466,
+              -0.04336231,
+              0.00054701004,
+              0.034879614,
+              0.017960642,
+              -0.062501945,
+              8.224154e-34,
+              -0.09450138,
+              0.013776636,
+              -0.025351105,
+              0.098992504,
+              0.045503527,
+              -0.02053458,
+              -0.029694881,
+              -0.059200566,
+              0.042453792,
+              0.0844487,
+              -0.043211546,
+              -0.0077362363,
+              0.049354795,
+              0.04203366,
+              -0.036539596,
+              0.014424774,
+              0.040357023,
+              -0.058971472,
+              0.010022987,
+              0.059877146,
+              -0.02790864,
+              0.034927685,
+              -0.087597504,
+              -0.060616262,
+              -0.0048867166,
+              0.08776906,
+              -0.0053599468,
+              -0.021816833,
+              -0.048162397,
+              0.046919785,
+              0.0083988905,
+              -0.0517289,
+              -0.020422187,
+              0.08581073,
+              -0.022597926,
+              0.034425046,
+              -0.014506674,
+              0.0031332907,
+              -0.04651877,
+              0.030281488,
+              0.039713897,
+              0.02969227,
+              -0.09310218,
+              0.051527865,
+              0.007809,
+              -0.05700871,
+              -0.041792583,
+              0.08987064,
+              -0.00813404,
+              -0.04082285,
+              -0.053487595,
+              -0.034378976,
+              -0.045253906,
+              -0.09715307,
+              -0.058194414,
+              0.06093547,
+              -0.009079956,
+              0.006918499,
+              0.012345728,
+              0.062036473,
+              -0.0060238577,
+              -0.0864295,
+              0.05872831,
+              0.053304974,
+              -0.05352623,
+              0.039521407,
+              -0.04498403,
+              0.0727911,
+              -0.039616212,
+              -0.05134442,
+              0.10334881,
+              0.02176773,
+              0.00016648973,
+              0.009423309,
+              0.022016358,
+              -0.006902813,
+              -0.128883,
+              -0.009864072,
+              -0.036396757,
+              -0.042481646,
+              0.004420737,
+              -0.047660243,
+              0.0065179355,
+              0.102602735,
+              -0.053166825,
+              0.07328581,
+              0.015810944,
+              -0.029149039,
+              0.025130944,
+              -0.063055776,
+              -0.043462534,
+              0.06719971,
+              0.014921177,
+              -0.0010985207,
+              -0.09869465,
+              -1.4682753e-08,
+              0.004611013,
+              -0.06715223,
+              0.07644809,
+              -0.019802453,
+              0.06737909,
+              0.044783685,
+              -0.050963327,
+              -0.0077186874,
+              -0.029319718,
+              0.028867716,
+              0.018877175,
+              -0.024279349,
+              0.04412064,
+              0.04416273,
+              0.03432814,
+              0.046517964,
+              0.02158077,
+              -0.001748483,
+              -0.0029956794,
+              0.014355785,
+              0.12525895,
+              0.03431845,
+              -0.014617591,
+              0.039184693,
+              -0.0023036227,
+              -0.014352919,
+              0.01010173,
+              0.02430961,
+              -0.041730728,
+              0.08832413,
+              -0.031459343,
+              0.030073628,
+              -0.0029376182,
+              0.0049478672,
+              0.09588392,
+              0.09396655,
+              0.01412568,
+              -0.077148266,
+              -0.039246846,
+              -0.01064901,
+              -0.008556093,
+              0.06409403,
+              -0.033037152,
+              -0.03049978,
+              0.0945846,
+              -0.008954658,
+              -0.029921891,
+              -0.132985,
+              0.059934624,
+              -0.011668423,
+              0.0071737366,
+              0.035627652,
+              0.0041028745,
+              0.056198087,
+              0.07656151,
+              -0.010067092,
+              0.05678312,
+              0.023536043,
+              -0.063770495,
+              0.08934554,
+              0.043756966,
+              0.04337246,
+              0.046287052,
+              -0.07039028
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 2,
+          "total_tokens": 2
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/72e075bf28e8.json

@@ -0,0 +1,800 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "togethercomputer/m2-bert-80M-32k-retrieval",
+      "input": "Hello, world!"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "togethercomputer/m2-bert-80M-32k-retrieval"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.017041557,
+              -0.07436493,
+              0.02897635,
+              -0.032216743,
+              0.0056444216,
+              -0.029015187,
+              0.06512343,
+              -0.040310342,
+              0.05263593,
+              0.0068842396,
+              0.019191971,
+              -0.0064884443,
+              -0.01664521,
+              0.014244285,
+              0.036390014,
+              -0.040292,
+              0.031780273,
+              0.0039553884,
+              -0.055303488,
+              -0.028992416,
+              -0.02059435,
+              0.05677091,
+              -0.043668333,
+              -0.014273451,
+              0.15328151,
+              -0.023603301,
+              -0.049825363,
+              0.007869072,
+              -0.010882995,
+              -0.033912696,
+              0.053697765,
+              -0.00093928695,
+              0.0017799847,
+              0.038871024,
+              -0.069678165,
+              -0.067093275,
+              0.025772842,
+              -0.057590123,
+              -0.015825877,
+              0.020131286,
+              0.020742312,
+              0.003915491,
+              -0.018451879,
+              0.020440312,
+              -0.023613403,
+              -0.039568678,
+              -0.013152008,
+              -0.01871725,
+              0.021348018,
+              -0.019964654,
+              0.038607903,
+              0.018397795,
+              -0.0063561443,
+              -0.018936336,
+              -0.060981557,
+              -0.02152846,
+              0.027057847,
+              0.0014626224,
+              -0.018241309,
+              -0.07473041,
+              -0.02377323,
+              -0.033910733,
+              0.02569418,
+              -0.024951216,
+              -0.0076659806,
+              -0.015425462,
+              0.006604636,
+              0.09833969,
+              -0.005054596,
+              0.008841989,
+              -0.01836461,
+              -0.018554095,
+              0.011605144,
+              -0.016599955,
+              -0.062196333,
+              -0.0037542647,
+              -0.025220644,
+              -0.027834827,
+              -0.020460974,
+              -0.050503097,
+              0.032119684,
+              -0.023387104,
+              0.050067227,
+              -0.05834235,
+              0.023189448,
+              -0.021862485,
+              0.023831544,
+              -0.016663097,
+              -0.041609522,
+              0.025361128,
+              0.002924296,
+              0.01852158,
+              0.08960255,
+              -0.003265466,
+              -0.058762494,
+              -0.06428431,
+              -0.014671485,
+              -0.046800107,
+              0.02691456,
+              -0.0059303525,
+              -0.015431455,
+              0.022179665,
+              0.014044907,
+              0.012218545,
+              0.0053836405,
+              -0.025096457,
+              0.009438382,
+              0.032498095,
+              0.06879721,
+              0.056900814,
+              0.019497631,
+              -0.122159146,
+              -0.106994465,
+              -0.017456975,
+              0.047223866,
+              0.06569824,
+              0.04780035,
+              0.018039258,
+              -0.0011028647,
+              -0.05067006,
+              0.0106863845,
+              0.027489506,
+              -0.014593985,
+              -0.039851535,
+              -0.09175489,
+              0.037555773,
+              -0.060439512,
+              0.008525801,
+              0.0071557434,
+              -0.057973035,
+              -0.054225244,
+              0.051505033,
+              -0.0008626373,
+              0.069083415,
+              0.064380065,
+              0.09843996,
+              0.0062191207,
+              -0.041505292,
+              -0.05381256,
+              -0.0073601264,
+              -0.03288613,
+              0.011711341,
+              -0.09244605,
+              0.0069717136,
+              -0.05722877,
+              0.041075893,
+              0.06521969,
+              -0.0018537377,
+              0.016272636,
+              0.008761483,
+              -0.029342752,
+              0.020412564,
+              -0.07015791,
+              0.033616304,
+              0.039998446,
+              0.01602917,
+              0.044467725,
+              -0.08176377,
+              -0.036885373,
+              0.03468746,
+              0.0024068495,
+              0.00056306267,
+              0.02546511,
+              -0.053339135,
+              -0.027220095,
+              -0.021510394,
+              0.054806393,
+              -0.005447777,
+              -0.05690438,
+              -0.028497366,
+              0.01873974,
+              -0.035461064,
+              -0.00019089226,
+              -0.04914238,
+              0.030303763,
+              0.013396073,
+              0.015789565,
+              -0.07714792,
+              -0.062155712,
+              -0.00677417,
+              0.02850476,
+              0.031491462,
+              0.014566345,
+              0.012163924,
+              0.11814501,
+              -0.0043511004,
+              -0.017920421,
+              0.004205825,
+              -0.0015928322,
+              -0.012145554,
+              0.01663168,
+              -0.071173735,
+              0.0029570858,
+              0.12899451,
+              0.004157568,
+              0.010501232,
+              0.07710632,
+              0.062119417,
+              0.021002673,
+              -0.023212241,
+              -0.04327007,
+              -0.0567023,
+              0.04590105,
+              0.0019161925,
+              0.02637205,
+              0.029331107,
+              -0.029769177,
+              -0.050466795,
+              -0.08057371,
+              0.007419741,
+              -0.008777471,
+              0.02217743,
+              0.013535721,
+              0.03426775,
+              0.04592361,
+              0.009423588,
+              -0.023030678,
+              -0.024462381,
+              0.054334357,
+              0.06710402,
+              0.077300854,
+              0.0300022,
+              -0.0035417816,
+              -0.0046773576,
+              -0.0927158,
+              -0.0218652,
+              -0.043468982,
+              -0.035734102,
+              -0.038873542,
+              -0.0412869,
+              -0.016015923,
+              0.0038303286,
+              0.08523618,
+              -0.05200533,
+              -0.014904317,
+              -0.016793448,
+              0.04478206,
+              -0.017161047,
+              0.02638292,
+              0.007849463,
+              -0.040533304,
+              -0.017599737,
+              0.047704253,
+              0.034988616,
+              -0.013908102,
+              0.044121094,
+              0.040395457,
+              -0.010402818,
+              0.0063570403,
+              -0.014962749,
+              0.025776524,
+              0.023681043,
+              0.006042675,
+              0.017647373,
+              0.016301101,
+              -0.07793374,
+              -0.004771094,
+              0.012728924,
+              -0.00047885205,
+              -0.051591527,
+              0.03612118,
+              -0.02209703,
+              0.052075963,
+              -0.021613466,
+              -0.026258182,
+              0.008102769,
+              -0.04963262,
+              0.00062747014,
+              -0.012579783,
+              0.076374784,
+              -0.047350414,
+              -0.007680664,
+              0.062471915,
+              -0.0061351187,
+              -0.043617643,
+              0.023878522,
+              -0.09653609,
+              0.018392054,
+              -0.039719462,
+              0.065271765,
+              0.034548305,
+              0.004219043,
+              -0.003628092,
+              0.0047836183,
+              0.0132732885,
+              -0.028140727,
+              -0.015683327,
+              -0.052812085,
+              -0.019410037,
+              0.06812139,
+              -0.041178964,
+              0.014646207,
+              -0.0037439142,
+              0.0003088275,
+              -0.04985693,
+              0.0223661,
+              0.008887433,
+              0.0049061268,
+              0.042707395,
+              -0.021471359,
+              -0.06471383,
+              0.0022036259,
+              0.030178884,
+              -0.002764245,
+              -0.0063233464,
+              -0.04146522,
+              -0.008236624,
+              0.0037351896,
+              -0.027550086,
+              -0.0137326885,
+              0.0055276263,
+              0.0016785853,
+              0.050191414,
+              0.02629574,
+              -0.009129228,
+              0.06351977,
+              -0.037435655,
+              0.0467174,
+              -0.012987377,
+              -0.007550927,
+              -0.004503205,
+              0.010520655,
+              0.064984836,
+              0.009879768,
+              0.055787366,
+              -0.042653065,
+              0.024189176,
+              0.0378726,
+              -0.032453574,
+              0.043519154,
+              0.020133087,
+              -0.055212636,
+              -0.016188117,
+              0.03764466,
+              -0.022142444,
+              0.11164031,
+              0.019020407,
+              -0.008950892,
+              0.0517199,
+              0.0014494535,
+              0.041113462,
+              -0.0912906,
+              -0.04723132,
+              0.008548748,
+              0.028231544,
+              0.023689618,
+              -0.039103802,
+              -0.034011997,
+              -0.04731894,
+              0.03309799,
+              -0.044572156,
+              -0.116778485,
+              -0.028786778,
+              0.05798776,
+              0.05287191,
+              -0.0039562676,
+              -0.08213019,
+              -0.01224603,
+              -0.012757768,
+              0.035721667,
+              0.012440343,
+              0.0053813523,
+              -0.072770126,
+              0.0066190604,
+              0.038976185,
+              -0.037760906,
+              -0.0031381482,
+              -0.052277293,
+              -0.016870236,
+              -0.053451907,
+              -0.05629483,
+              -0.034493946,
+              -0.0048654405,
+              0.022051724,
+              0.028501945,
+              0.025858566,
+              -0.023936177,
+              -0.098391004,
+              -0.030646492,
+              -0.049461726,
+              -0.00086931954,
+              0.03593346,
+              0.015843417,
+              -0.03276966,
+              0.008957432,
+              -0.022735167,
+              -0.012159252,
+              0.07607085,
+              -0.059834506,
+              0.004478244,
+              0.03439635,
+              0.03683821,
+              0.062883355,
+              0.054430448,
+              -0.029807799,
+              0.0032295138,
+              0.08891875,
+              -0.026941199,
+              -0.00618463,
+              -0.022683868,
+              -0.024138795,
+              -0.036633875,
+              0.02097464,
+              -0.003001584,
+              0.020455033,
+              0.043717608,
+              0.06566654,
+              -0.029039463,
+              -0.0066977167,
+              -0.04504434,
+              0.022257777,
+              0.054422457,
+              0.029796708,
+              0.009008146,
+              0.028205348,
+              0.06255052,
+              -0.004475601,
+              0.059329458,
+              -0.038065027,
+              -0.027933009,
+              -0.07060949,
+              0.013978787,
+              -0.051300917,
+              0.02945564,
+              -0.008552103,
+              -0.009436655,
+              0.039747514,
+              -0.016741823,
+              0.04740887,
+              0.03521937,
+              -0.012574282,
+              -0.089222826,
+              -0.043515395,
+              -0.04158566,
+              0.0016020355,
+              0.02684753,
+              -0.019394692,
+              -0.02156877,
+              0.06316388,
+              0.01663444,
+              0.015482924,
+              0.047349654,
+              -0.028341234,
+              0.013805591,
+              -0.010708488,
+              -0.07627738,
+              0.08611209,
+              0.0089956885,
+              0.034438204,
+              0.016312746,
+              -0.03412846,
+              0.0770598,
+              -0.06790466,
+              0.036359854,
+              0.08038976,
+              0.023465984,
+              -0.019832904,
+              -0.0011524013,
+              -0.03804293,
+              0.04106918,
+              -0.028220456,
+              0.032340813,
+              -0.030669356,
+              -0.004353358,
+              -0.019439798,
+              0.0020563425,
+              0.03015629,
+              -0.06430176,
+              0.0034439075,
+              -0.045720384,
+              -0.06526568,
+              -0.0004192516,
+              -0.016580455,
+              -0.012596616,
+              0.039126,
+              -0.04699455,
+              -0.008973794,
+              0.015056125,
+              0.018929023,
+              -0.07840811,
+              -0.014792519,
+              -0.0044317124,
+              0.019588342,
+              0.035912346,
+              -0.035739247,
+              0.058755044,
+              -0.01856197,
+              0.021155646,
+              -0.073580906,
+              -0.04310776,
+              -0.023147091,
+              -0.010232029,
+              0.06352039,
+              0.039570276,
+              0.020424508,
+              0.051613245,
+              0.013395984,
+              -0.003908009,
+              -0.04643392,
+              0.019592889,
+              -0.008484923,
+              0.0031434586,
+              -0.046069775,
+              -0.01765311,
+              -0.041277196,
+              -0.070297986,
+              0.012561737,
+              -0.003500738,
+              -0.01729488,
+              -0.0033254062,
+              0.053035453,
+              -0.054218896,
+              -0.029708259,
+              -0.0047281524,
+              0.019236762,
+              -0.12249525,
+              0.03018237,
+              -0.028753102,
+              -0.031858314,
+              0.0811298,
+              -0.005711499,
+              -0.057587985,
+              0.014153141,
+              0.0006705577,
+              -0.024263157,
+              0.016729265,
+              -0.03195949,
+              -0.007259763,
+              -0.0035231581,
+              -0.03890975,
+              0.011460382,
+              -0.06591321,
+              -0.023756726,
+              -0.023958001,
+              0.030074941,
+              -0.0040949634,
+              -0.048368257,
+              -0.029692868,
+              0.027246583,
+              -0.024747347,
+              0.014442731,
+              -0.00832639,
+              -0.0002390868,
+              -0.013635633,
+              0.0035843733,
+              0.02354072,
+              -0.012829061,
+              -0.0060750768,
+              -0.044952527,
+              -0.05725624,
+              0.031746052,
+              -0.024419094,
+              0.032444403,
+              -0.029308707,
+              0.034302235,
+              -0.022495607,
+              0.015296428,
+              -0.0057196384,
+              -7.8588724e-05,
+              0.060303975,
+              0.06299601,
+              0.028222265,
+              -0.0071411408,
+              0.015196491,
+              0.02031155,
+              0.039635558,
+              0.079736926,
+              0.008736669,
+              -0.023079613,
+              -0.04490686,
+              -0.021764707,
+              -0.015199573,
+              0.036019534,
+              -0.0046079857,
+              0.04429082,
+              -0.04291344,
+              -0.05991891,
+              -0.006501417,
+              0.010603077,
+              0.03435066,
+              -0.065568395,
+              -0.04424192,
+              0.035055783,
+              0.019717937,
+              0.032764338,
+              0.021240309,
+              -0.01646063,
+              0.007835414,
+              0.06857148,
+              -0.013750999,
+              0.028333688,
+              -0.078255735,
+              -0.047899257,
+              -0.0006370693,
+              0.012606231,
+              0.012178417,
+              -0.013057751,
+              -0.008095854,
+              -0.013466724,
+              0.019036459,
+              -0.025450038,
+              0.021131655,
+              -0.02505666,
+              0.012961284,
+              0.0004236046,
+              -0.023920864,
+              -0.055114083,
+              0.082351916,
+              0.028973032,
+              0.025259241,
+              0.098259576,
+              -0.007385416,
+              0.003546012,
+              -0.05316339,
+              -0.04186183,
+              0.043638214,
+              -0.069299474,
+              -0.013284585,
+              -0.010019175,
+              0.012883975,
+              0.014200739,
+              -0.013508286,
+              0.0086570075,
+              -0.020393575,
+              0.10617594,
+              0.028786503,
+              -0.018674662,
+              0.026763268,
+              -0.0062548965,
+              -0.07215284,
+              0.055464335,
+              0.0029595464,
+              -0.009364344,
+              -0.096402094,
+              0.02823341,
+              -0.022853011,
+              0.04750492,
+              0.008378555,
+              0.016491622,
+              0.01860681,
+              0.048116222,
+              0.106049344,
+              -0.028929656,
+              -0.008896546,
+              0.033615295,
+              -0.0070807124,
+              -0.05684197,
+              -0.061439563,
+              0.0060220268,
+              0.046171866,
+              -0.01574131,
+              -0.07562956,
+              0.0024098414,
+              0.0006304895,
+              -0.07831614,
+              0.060869616,
+              0.00076000375,
+              -0.008209363,
+              -0.04139266,
+              -0.085268535,
+              -0.028194478,
+              -0.024567788,
+              -0.04218179,
+              0.023546752,
+              0.036236234,
+              0.017199656,
+              -0.03315456,
+              -0.023814544,
+              0.038755447,
+              -0.023165299,
+              -0.049283065,
+              -0.006907019,
+              0.040826146,
+              0.017533792,
+              -0.036849793,
+              -0.015506943,
+              -0.010768763,
+              -0.08758806,
+              -0.0295733,
+              0.055843282,
+              -0.012555046,
+              0.0076235603,
+              0.008802991,
+              0.026661193,
+              -0.023899797,
+              0.043548774,
+              -0.034339137,
+              -0.027354732,
+              -0.07583677,
+              0.020500224,
+              0.036802996,
+              0.031019075,
+              0.04605757,
+              -0.004433706,
+              0.0108612785,
+              0.050121468,
+              -0.07816735,
+              -0.014776514,
+              -0.04565195,
+              -0.0036854912,
+              0.0075577567,
+              -0.017044865,
+              0.030597543,
+              -0.013623054,
+              -0.0648466,
+              -0.0318741,
+              -0.059455115,
+              -0.024783187,
+              -0.0088010235,
+              0.11127796,
+              0.03429834,
+              -0.010424589,
+              -0.06355135,
+              0.034265812,
+              0.02680333,
+              -0.007930513,
+              0.030092249,
+              0.008321974,
+              0.03125566,
+              -0.06832331,
+              -0.0076806936,
+              0.034010306,
+              -0.087202646,
+              -0.047684345,
+              0.06384632,
+              -0.026591811,
+              -0.0016003181,
+              0.05721666,
+              -0.0024700803,
+              -0.029714238,
+              0.07761957,
+              -0.04561395,
+              -0.053199258,
+              0.030417573,
+              -0.01958724,
+              0.0012449475,
+              -0.04003076,
+              0.08825553,
+              -0.023196172,
+              -0.08629044,
+              -0.049815316,
+              0.027229005,
+              0.0021765123,
+              0.03438692,
+              -0.09314263,
+              -0.019655729,
+              0.018762926,
+              0.025670087,
+              -0.017116003,
+              0.031716976,
+              -0.05509443,
+              0.032953184,
+              -0.02264915,
+              0.04861606,
+              -0.050201602,
+              0.033154316,
+              0.009971947,
+              -0.037610047,
+              0.016600395,
+              -0.031037569,
+              -0.015495428,
+              0.026365642,
+              -0.043527953,
+              0.055781424,
+              0.06780075,
+              -0.015966192,
+              0.03201043,
+              0.028026119
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "togethercomputer/m2-bert-80M-32k-retrieval",
+        "object": "list",
+        "usage": null
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/7354ec181984.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-07-31T17:51:16.201313167Z",
+        "created_at": "2025-09-03T17:39:54.374714Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 27475921912,
-        "load_duration": 40564716,
+        "total_duration": 6321793333,
+        "load_duration": 182255958,
         "prompt_eval_count": 25,
-        "prompt_eval_duration": 964907432,
+        "prompt_eval_duration": 67964459,
         "eval_count": 150,
-        "eval_duration": 26469935419,
+        "eval_duration": 6070867875,
         "response": "The smallest country in the world is the Vatican City, which has a total area of approximately 0.44 km\u00b2 (0.17 sq mi). It is an independent city-state located within Rome, Italy, and is home to the Pope and the central government of the Catholic Church.\n\nTo put that into perspective, the Vatican City is smaller than a golf course! Despite its tiny size, it has its own government, currency, postal system, and even its own police force. It's also home to numerous iconic landmarks like St. Peter's Basilica and the Sistine Chapel.\n\nInterestingly, the Vatican City is not only the smallest country in the world but also the most densely populated, with a population of just over 800 people!",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/75d0dd9d0fa3.json

@@ -45,15 +45,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama3.2:3b-instruct-fp16",
-        "created_at": "2025-08-04T22:55:10.58267Z",
+        "created_at": "2025-09-03T17:36:17.508028Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 1981967792,
-        "load_duration": 63184458,
+        "total_duration": 1529591917,
+        "load_duration": 84990667,
         "prompt_eval_count": 119,
-        "prompt_eval_duration": 259000000,
+        "prompt_eval_duration": 189045583,
         "eval_count": 29,
-        "eval_duration": 1582000000,
+        "eval_duration": 1254813583,
         "response": "{ \"name\": \"Michael Jordan\", \"year_born\": \"1963\", \"year_retired\": \"2003\"}\n    ",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/7b25b702ea18.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "test query"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              0.06829306,
+              0.061738,
+              -0.0064223274,
+              0.08267553,
+              -0.07827752,
+              0.026546001,
+              0.13129343,
+              0.041391023,
+              -0.01950488,
+              -0.027131394,
+              0.08875853,
+              -0.10276945,
+              0.05070562,
+              -0.07138499,
+              -0.0092889285,
+              -0.039247777,
+              0.028884362,
+              -0.010484688,
+              -0.02469515,
+              -0.0354649,
+              -0.04093021,
+              -0.009903105,
+              -0.026185337,
+              0.057967436,
+              -0.00060980336,
+              0.007659294,
+              0.013928803,
+              -0.0016587646,
+              0.044655163,
+              -0.058990903,
+              -0.037958965,
+              0.037799176,
+              -0.033270117,
+              0.071682036,
+              0.09722083,
+              -0.08261939,
+              0.027622383,
+              -0.014190519,
+              0.01816939,
+              -0.002717151,
+              -0.02426505,
+              -0.11493204,
+              0.0851599,
+              -0.016752614,
+              -0.006310121,
+              0.065255314,
+              -0.058001935,
+              0.096675195,
+              -0.01419834,
+              -0.0068260576,
+              -0.09889976,
+              -0.015109596,
+              -0.07833432,
+              -0.035589334,
+              -0.008278154,
+              -0.013655421,
+              -0.07625151,
+              -0.030405698,
+              -0.013589333,
+              0.050117858,
+              -0.010591754,
+              -0.038398717,
+              0.067407176,
+              0.03565695,
+              0.010748793,
+              -0.0782303,
+              -0.006898065,
+              -0.03009224,
+              0.05595709,
+              -0.076849714,
+              -0.009063107,
+              -0.0028242348,
+              -0.02941444,
+              0.06881705,
+              0.013745148,
+              0.03078439,
+              -0.036471423,
+              -0.07147355,
+              0.054742936,
+              -0.028959772,
+              -0.06466119,
+              -0.05974295,
+              -0.06766193,
+              0.022777116,
+              0.079530336,
+              0.051767077,
+              0.14789894,
+              -0.0024908637,
+              -0.05542459,
+              -0.027760198,
+              0.019384151,
+              0.06692773,
+              -0.07952434,
+              0.019047031,
+              -0.00097613735,
+              0.013479467,
+              0.038207904,
+              -0.040212464,
+              0.06499357,
+              0.13929029,
+              0.0592868,
+              0.018087199,
+              -0.04910378,
+              -0.057469312,
+              -0.17034933,
+              0.009854021,
+              0.04478709,
+              -0.08707103,
+              0.046889827,
+              -0.020303966,
+              -0.062274974,
+              0.030287566,
+              0.04991786,
+              -0.030625034,
+              -0.007196787,
+              -0.060630832,
+              -0.0057445914,
+              0.028697284,
+              -0.055902485,
+              -0.0060850815,
+              0.075516894,
+              0.07304865,
+              -0.03200336,
+              -0.027994294,
+              -0.0013179975,
+              0.02373418,
+              0.082337655,
+              -2.0787389e-33,
+              0.014712573,
+              -0.084956154,
+              0.059368864,
+              -0.00785449,
+              -0.015981624,
+              0.02598549,
+              0.037614744,
+              0.12561654,
+              -0.04002324,
+              0.02472032,
+              0.014450717,
+              -0.06304021,
+              0.034111217,
+              -0.00766782,
+              0.008186535,
+              0.10461876,
+              0.018852819,
+              -0.021535609,
+              -0.04381762,
+              0.05679568,
+              0.01621111,
+              -0.0734938,
+              0.020150887,
+              0.05246773,
+              0.015011716,
+              -0.06588331,
+              -0.03257114,
+              0.025002314,
+              0.018430108,
+              -0.00030111038,
+              -0.06266604,
+              -0.006196726,
+              -0.16044672,
+              0.028114004,
+              0.032982383,
+              0.037261836,
+              0.0540566,
+              -0.0079226745,
+              -0.008597091,
+              0.054075282,
+              -0.046998158,
+              -0.03870267,
+              0.08493371,
+              -0.005938313,
+              0.021924777,
+              -0.05206361,
+              -0.047436308,
+              -0.054906387,
+              0.03400277,
+              -0.028335828,
+              -0.032045983,
+              -0.0013805287,
+              -0.04042137,
+              -0.017744336,
+              0.052251115,
+              0.0038320236,
+              0.008692022,
+              0.03270182,
+              0.010805367,
+              0.11194987,
+              -0.019722551,
+              -0.04577441,
+              -0.002028829,
+              0.020897591,
+              -0.006168528,
+              -0.0017238662,
+              -0.006808375,
+              -0.08133367,
+              0.091827765,
+              0.048646383,
+              0.07771223,
+              -0.05870435,
+              0.006373254,
+              0.0036029797,
+              -0.071249805,
+              0.022061123,
+              0.019477166,
+              0.10132688,
+              0.006618212,
+              -0.044631813,
+              0.06139753,
+              -0.09197761,
+              -0.013284173,
+              0.014608393,
+              -0.01761416,
+              0.0073858253,
+              0.0062043094,
+              -0.048021033,
+              0.013127433,
+              -0.077592075,
+              0.014133566,
+              0.035386372,
+              -0.02616333,
+              0.0027075391,
+              0.08635036,
+              9.132231e-34,
+              -0.022040669,
+              0.05085595,
+              -0.027267562,
+              0.02862394,
+              0.0137278,
+              -0.07108621,
+              0.09040417,
+              -0.09064723,
+              -0.0656353,
+              0.06688156,
+              0.06701843,
+              -0.05015593,
+              0.01906404,
+              -0.04147956,
+              0.012601856,
+              0.06909683,
+              0.028203059,
+              -0.0709644,
+              -0.061153468,
+              0.031663477,
+              -0.09626921,
+              0.13134153,
+              -0.003593543,
+              -0.027185699,
+              -0.06297406,
+              -0.00092433795,
+              -0.008680087,
+              -0.031325806,
+              -0.018586429,
+              0.011512126,
+              0.071864344,
+              -0.071975954,
+              -0.005884031,
+              0.09355209,
+              0.046686243,
+              -0.031970512,
+              0.06956754,
+              -0.045880646,
+              0.010095539,
+              0.064092614,
+              0.07247815,
+              0.04723167,
+              0.048781574,
+              0.06763336,
+              0.0054456857,
+              0.035764687,
+              0.018254038,
+              -0.03819517,
+              0.050082564,
+              0.04140595,
+              -0.025459196,
+              0.021584416,
+              0.014274055,
+              -0.007126868,
+              -0.014268015,
+              -0.010105026,
+              -0.09164537,
+              0.009354007,
+              0.004333732,
+              -0.009582354,
+              -0.029860867,
+              0.17471065,
+              -0.0045884773,
+              0.05782756,
+              -0.044819925,
+              -0.051430847,
+              -0.045887176,
+              0.0074449414,
+              0.0054387357,
+              0.039599653,
+              -0.056232683,
+              -0.002221041,
+              0.047835752,
+              -0.039582185,
+              0.027316216,
+              0.039718047,
+              -0.07969795,
+              0.03511298,
+              0.029242206,
+              0.010144028,
+              -0.03904501,
+              -0.027879883,
+              -0.040858228,
+              0.04611512,
+              -0.06931006,
+              0.061977647,
+              0.03922111,
+              0.025860278,
+              0.0064425017,
+              0.053613506,
+              0.069628745,
+              -0.007990142,
+              -0.038263973,
+              -0.10954397,
+              0.018542184,
+              -1.33346125e-08,
+              -0.025668526,
+              -0.07473254,
+              -0.019855365,
+              0.0384919,
+              0.027314084,
+              -0.010875396,
+              -0.035207637,
+              0.036075134,
+              -0.063237526,
+              0.011492366,
+              0.03342596,
+              -0.012063488,
+              0.0039839908,
+              0.016522188,
+              -0.008002217,
+              -0.04168924,
+              -0.07092195,
+              0.008746656,
+              0.004452133,
+              -0.03877822,
+              -0.051253635,
+              0.01774984,
+              -0.018253444,
+              0.04394154,
+              -0.042883426,
+              0.08245372,
+              0.015452854,
+              0.022076968,
+              0.04442366,
+              0.022832815,
+              0.08296971,
+              -0.01261236,
+              0.013092747,
+              -0.06689178,
+              0.0478462,
+              -0.04507667,
+              0.006519156,
+              0.0055980994,
+              -0.019575223,
+              -0.01730519,
+              -0.03837497,
+              -0.00043787624,
+              -0.008650636,
+              -0.026787039,
+              -0.06598753,
+              -0.14336495,
+              0.041543495,
+              -0.048590284,
+              0.012749011,
+              -0.08499328,
+              -0.010950221,
+              -0.038154602,
+              0.030090204,
+              -0.03886871,
+              -0.03670644,
+              0.046492297,
+              0.03623469,
+              0.052362714,
+              -0.09623828,
+              -0.04149126,
+              0.050219554,
+              -2.084757e-05,
+              0.0019338154,
+              0.019553935
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 2,
+          "total_tokens": 2
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/7b4815aba6c5.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.222059Z",
+          "created_at": "2025-09-03T17:37:48.840898Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.273466Z",
+          "created_at": "2025-09-03T17:37:48.883619Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.325562Z",
+          "created_at": "2025-09-03T17:37:48.92504Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.379223Z",
+          "created_at": "2025-09-03T17:37:48.966274Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.436435Z",
+          "created_at": "2025-09-03T17:37:49.007525Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.48928Z",
+          "created_at": "2025-09-03T17:37:49.049125Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.547102Z",
+          "created_at": "2025-09-03T17:37:49.090893Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.60579Z",
+          "created_at": "2025-09-03T17:37:49.132101Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.660149Z",
+          "created_at": "2025-09-03T17:37:49.17401Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.719166Z",
+          "created_at": "2025-09-03T17:37:49.216115Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.773893Z",
+          "created_at": "2025-09-03T17:37:49.257109Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.827636Z",
+          "created_at": "2025-09-03T17:37:49.298731Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,7 +238,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.905205Z",
+          "created_at": "2025-09-03T17:37:49.338833Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -256,7 +256,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:59.959347Z",
+          "created_at": "2025-09-03T17:37:49.38053Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -274,7 +274,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:00.037904Z",
+          "created_at": "2025-09-03T17:37:49.421378Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -292,7 +292,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:00.093527Z",
+          "created_at": "2025-09-03T17:37:49.462646Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -310,7 +310,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:00.151329Z",
+          "created_at": "2025-09-03T17:37:49.503814Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -328,7 +328,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:00.209463Z",
+          "created_at": "2025-09-03T17:37:49.545397Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -346,15 +346,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:00.268012Z",
+          "created_at": "2025-09-03T17:37:49.586834Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1981034959,
-          "load_duration": 53445084,
+          "total_duration": 1409239209,
+          "load_duration": 118889250,
           "prompt_eval_count": 368,
-          "prompt_eval_duration": 880000000,
+          "prompt_eval_duration": 543077166,
           "eval_count": 19,
-          "eval_duration": 1046000000,
+          "eval_duration": 746733584,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/7e6806cba34a.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:14.382398152Z",
+          "created_at": "2025-09-03T17:41:43.22891Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:14.561084788Z",
+          "created_at": "2025-09-03T17:41:43.268911Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:14.743154167Z",
+          "created_at": "2025-09-03T17:41:43.310121Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:14.920818124Z",
+          "created_at": "2025-09-03T17:41:43.35053Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:15.099067906Z",
+          "created_at": "2025-09-03T17:41:43.391033Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:15.274401879Z",
+          "created_at": "2025-09-03T17:41:43.431414Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:15.449669669Z",
+          "created_at": "2025-09-03T17:41:43.471553Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:15.626501213Z",
+          "created_at": "2025-09-03T17:41:43.512029Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:15.802614623Z",
+          "created_at": "2025-09-03T17:41:43.55268Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:15.978698104Z",
+          "created_at": "2025-09-03T17:41:43.594309Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,7 +201,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:16.160654179Z",
+          "created_at": "2025-09-03T17:41:43.635445Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -219,7 +219,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:16.338412914Z",
+          "created_at": "2025-09-03T17:41:43.676541Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -237,15 +237,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-31T17:59:16.521646436Z",
+          "created_at": "2025-09-03T17:41:43.717809Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 4555044563,
-          "load_duration": 43101307,
+          "total_duration": 820540625,
+          "load_duration": 111045959,
           "prompt_eval_count": 29,
-          "prompt_eval_duration": 2371036213,
+          "prompt_eval_duration": 219693291,
           "eval_count": 13,
-          "eval_duration": 2140342701,
+          "eval_duration": 489282542,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/7ef63231b9f8.json

@@ -0,0 +1,56 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://localhost:8080/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "Qwen/Qwen3-0.6B",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Which planet has rings around it with a name starting with letter S?"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "Qwen/Qwen3-0.6B"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "<think>\nOkay, so the user is asking which planet has rings around it and its name starts with the letter S. Let me think... I know that the Sun is a star, not a planet. So the Moon is a natural satellite, which has the Moon's name and rings. But the Moon's name starts with M, not S. The Earth has the name Earth, but the rings aren't really around the Earth in any real sense. Mars has a thin ring of dust. Venus and Mercury don't have rings in the sense of planetary rings as we know. Wait, maybe the answer is the Moon, even though it's not the same as the name starting with S. But the question says a planet, so if there's a planet named S, that would be it. But actually, the only planet with rings is Jupiter. Wait, Jupiter has a famous system of rings. But why does the question mention a planet with a name starting with S? Maybe there's a trick. Let me double-check. Jupiter's name starts with J, so maybe the answer is Venus? But Venus doesn't have rings. Mercury, too, doesn't. The Moon, as a planet, a dwarf planet, and has rings. Despite the name, the rings are around it. So the answer would be the Moon. Therefore, the planet with rings and name starting with S is the Moon.\n</think>\n\nThe planet with rings around it and a name starting with the letter **S** is the **Moon**. Though its name doesn't start with an **S**, it is technically a dwarf planet and has the rings in its orbit. Oops Saturn!",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": null,
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            }
+          }
+        ],
+        "created": 1757550394,
+        "model": "Qwen/Qwen3-0.6B",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": "3.3.5-dev0-sha-1b90c50",
+        "usage": {
+          "completion_tokens": 336,
+          "prompt_tokens": 22,
+          "total_tokens": 358,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/802f60021837.json

@@ -0,0 +1,422 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "http://0.0.0.0:11434/v1/v1/embeddings",
+    "headers": {},
+    "body": {
+      "model": "all-minilm:l6-v2",
+      "input": [
+        "What is Python programming language?"
+      ],
+      "encoding_format": "float"
+    },
+    "endpoint": "/v1/embeddings",
+    "model": "all-minilm:l6-v2"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.create_embedding_response.CreateEmbeddingResponse",
+      "__data__": {
+        "data": [
+          {
+            "embedding": [
+              -0.062304743,
+              0.04315718,
+              -0.056847535,
+              0.03486019,
+              -0.045148205,
+              -0.1325256,
+              0.021795923,
+              0.039035086,
+              -0.048403695,
+              -0.03187157,
+              -0.03934502,
+              0.006355416,
+              0.07870429,
+              -0.004275144,
+              0.023635335,
+              -0.02171452,
+              -0.055756103,
+              -0.009452624,
+              0.03968397,
+              -0.11446917,
+              -0.011574315,
+              0.06161675,
+              -0.026243819,
+              0.024376081,
+              0.029439807,
+              -0.0035745306,
+              -0.0014413354,
+              -0.0031348146,
+              0.0137771955,
+              -0.00021878166,
+              -0.0148119675,
+              0.08438267,
+              0.06679146,
+              0.042289164,
+              0.0077238376,
+              0.073178865,
+              -0.008341517,
+              -0.094652176,
+              -0.09245101,
+              0.0075944075,
+              -0.07389992,
+              0.015481098,
+              -0.04405396,
+              -0.04497366,
+              -0.041315924,
+              0.06968346,
+              -0.027464444,
+              0.014380017,
+              -0.036109854,
+              -0.006690219,
+              -0.080297194,
+              -5.8296577e-05,
+              -0.03897778,
+              -0.049029846,
+              0.017797105,
+              -0.0064906515,
+              0.05977029,
+              -0.0031445406,
+              -0.024804324,
+              -0.114971094,
+              -0.047434244,
+              0.018489277,
+              -0.009801151,
+              0.09573786,
+              -0.009445709,
+              -0.035714474,
+              -0.031265706,
+              -0.0032087746,
+              0.07714283,
+              -0.076175354,
+              -0.11878057,
+              -0.06322687,
+              -0.0045974515,
+              0.06524851,
+              0.045755487,
+              -0.13797933,
+              0.045973603,
+              -0.03356543,
+              -0.013575197,
+              0.004536992,
+              0.01706251,
+              -0.0016689816,
+              -0.051292486,
+              0.10251468,
+              0.015364908,
+              -0.05339754,
+              0.046751976,
+              0.11428272,
+              -0.0060051866,
+              0.010296865,
+              -0.03160346,
+              -0.051935352,
+              0.02092994,
+              0.008887596,
+              -0.069010794,
+              0.08132733,
+              0.012102074,
+              -0.06409327,
+              -0.036342084,
+              0.046690084,
+              0.011248327,
+              -0.050334014,
+              0.073782355,
+              -0.02119414,
+              0.0324611,
+              -0.026148362,
+              0.06814877,
+              -0.03795885,
+              0.030811384,
+              -0.037118603,
+              -0.036956605,
+              -0.02943471,
+              -0.0328876,
+              -0.00579801,
+              0.04255975,
+              0.05469473,
+              -0.01927437,
+              0.12277417,
+              0.0037985598,
+              0.032079652,
+              0.023717156,
+              0.019211154,
+              0.019987307,
+              -0.012261412,
+              -0.032464176,
+              -0.004472998,
+              -0.03568547,
+              -6.953471e-33,
+              -0.02200053,
+              -0.06861985,
+              -0.035355665,
+              0.008892092,
+              0.07110619,
+              -0.02524488,
+              0.091491714,
+              -0.009333656,
+              -0.059515916,
+              -0.03471947,
+              0.04331791,
+              0.033350475,
+              0.02423151,
+              0.08795865,
+              0.020580785,
+              -0.00087637454,
+              -0.012995603,
+              0.088356934,
+              0.04568453,
+              0.025818799,
+              0.054319557,
+              0.09676607,
+              0.02314351,
+              0.024316499,
+              0.014192086,
+              -0.01867069,
+              -0.024500258,
+              -0.032566376,
+              0.025218401,
+              0.016804473,
+              -0.07628905,
+              0.012665322,
+              -0.021314982,
+              0.006895667,
+              0.030793479,
+              -0.00033363912,
+              0.0005291749,
+              -0.08589274,
+              0.040542576,
+              0.0062958263,
+              -0.009977536,
+              0.0016065374,
+              0.012649728,
+              -0.036491103,
+              -0.023085777,
+              0.012404348,
+              -0.0051287347,
+              0.020217113,
+              -0.08761001,
+              0.0451902,
+              -0.0012827619,
+              -0.06574815,
+              0.07477121,
+              0.08403992,
+              -0.01390955,
+              0.05589554,
+              0.019330526,
+              -0.019641383,
+              -0.016001293,
+              -0.02915193,
+              0.037374426,
+              0.068089314,
+              0.069200926,
+              -0.007668733,
+              0.021160824,
+              0.040417258,
+              0.035068225,
+              0.082075246,
+              0.08809441,
+              0.05050193,
+              -0.059343174,
+              0.04576526,
+              -0.025118835,
+              0.03583576,
+              -0.028081506,
+              0.019838363,
+              0.033905286,
+              -0.07977674,
+              0.023003135,
+              0.062460173,
+              -0.034886148,
+              -0.05390937,
+              -0.016114287,
+              -0.0057315156,
+              -0.03051132,
+              -0.02269694,
+              -0.010376983,
+              0.06762264,
+              -0.010560655,
+              -0.09605588,
+              -0.07854035,
+              -0.08528194,
+              0.029969428,
+              -0.0059528793,
+              -0.039581347,
+              2.9781768e-33,
+              0.011482255,
+              0.010417832,
+              -0.0698601,
+              0.019292813,
+              -0.08453582,
+              -0.08570265,
+              0.06624837,
+              0.063025005,
+              0.050434116,
+              0.033736084,
+              -0.0058885855,
+              -0.069622226,
+              0.12551048,
+              0.021380005,
+              0.07413853,
+              0.0342258,
+              -0.045818888,
+              0.014834041,
+              -0.012672501,
+              0.0036430089,
+              -0.08024709,
+              0.06730083,
+              -0.056032285,
+              -0.086702436,
+              -0.027874194,
+              -0.03391202,
+              -0.03872441,
+              -0.07792124,
+              -0.017794719,
+              0.061800934,
+              0.014696384,
+              0.019996569,
+              -0.08146178,
+              0.052340467,
+              0.06287676,
+              -0.0015751559,
+              0.040512506,
+              -0.027605608,
+              -0.009630798,
+              -0.017303543,
+              0.11392578,
+              0.044186074,
+              0.035317622,
+              0.12113664,
+              0.018812222,
+              0.049269576,
+              -0.036081262,
+              0.07789768,
+              -0.0296637,
+              -0.07068735,
+              -0.006731622,
+              0.0060941395,
+              0.042274125,
+              -0.039680813,
+              -0.048600707,
+              -0.03980193,
+              0.032409266,
+              0.03371183,
+              -0.092499994,
+              -0.049876206,
+              -0.06597403,
+              -0.042388365,
+              0.031259395,
+              0.011791109,
+              -0.04424881,
+              0.04685171,
+              -0.12302249,
+              -0.034650978,
+              -0.01387166,
+              -0.13122807,
+              0.1448325,
+              0.0056148693,
+              -0.0031096544,
+              0.022904772,
+              -0.07642485,
+              0.016454488,
+              -0.019540928,
+              -0.024970472,
+              -0.068574235,
+              0.07073104,
+              0.026643677,
+              -0.035163663,
+              -0.0015607082,
+              0.029314166,
+              -0.08943546,
+              -0.022545528,
+              -0.031130569,
+              0.053781237,
+              0.007896568,
+              0.023091432,
+              -0.0043701245,
+              0.05380369,
+              0.01729408,
+              0.05636822,
+              -0.05328019,
+              -1.3478804e-08,
+              -0.039678477,
+              0.013365443,
+              0.036817312,
+              0.009736139,
+              0.004703614,
+              0.06661744,
+              0.02291141,
+              -0.047423527,
+              -0.04049001,
+              0.0068159057,
+              0.008662143,
+              -0.006292634,
+              -0.045681197,
+              -0.06387613,
+              -0.013174571,
+              0.11696965,
+              0.016895585,
+              -0.0013498863,
+              0.023227682,
+              0.022274282,
+              0.07852807,
+              -0.04508963,
+              -0.009177306,
+              0.06640095,
+              -0.06651727,
+              -0.015498115,
+              0.054094598,
+              0.07642527,
+              0.0082470365,
+              -0.12409585,
+              0.01265297,
+              -0.017635401,
+              -0.020622984,
+              0.03250185,
+              -0.012997484,
+              0.022324847,
+              0.010529934,
+              -0.0883164,
+              0.021471445,
+              -0.0029947716,
+              -0.03183814,
+              0.0718419,
+              0.010377949,
+              0.0035974192,
+              0.048932698,
+              0.07039089,
+              -0.03657371,
+              -0.035186097,
+              -0.03655875,
+              -0.07017832,
+              -0.030322824,
+              0.028595895,
+              -0.019070871,
+              -0.0025186248,
+              0.021279149,
+              0.07436103,
+              -0.114249244,
+              -0.027311146,
+              -0.0107884705,
+              0.010422842,
+              -0.022787437,
+              0.11515081,
+              0.18532182,
+              -0.026544156
+            ],
+            "index": 0,
+            "object": "embedding"
+          }
+        ],
+        "model": "all-minilm:l6-v2",
+        "object": "list",
+        "usage": {
+          "prompt_tokens": 6,
+          "total_tokens": 6
+        }
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/80e4404d8987.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.463658Z",
+          "created_at": "2025-09-03T17:37:46.708948Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.51846Z",
+          "created_at": "2025-09-03T17:37:46.749031Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.569676Z",
+          "created_at": "2025-09-03T17:37:46.790192Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.621666Z",
+          "created_at": "2025-09-03T17:37:46.831093Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.675114Z",
+          "created_at": "2025-09-03T17:37:46.873135Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.727649Z",
+          "created_at": "2025-09-03T17:37:46.91375Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.780249Z",
+          "created_at": "2025-09-03T17:37:46.95439Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.834148Z",
+          "created_at": "2025-09-03T17:37:46.995224Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.885509Z",
+          "created_at": "2025-09-03T17:37:47.035887Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,15 +184,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:13:56.936635Z",
+          "created_at": "2025-09-03T17:37:47.076806Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1572591291,
-          "load_duration": 77121041,
+          "total_duration": 2069654958,
+          "load_duration": 177579833,
           "prompt_eval_count": 31,
-          "prompt_eval_duration": 1019000000,
+          "prompt_eval_duration": 1521851250,
           "eval_count": 10,
-          "eval_duration": 474000000,
+          "eval_duration": 369478042,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/8295382a8e7c.json

@@ -1,7 +1,7 @@
 {
   "request": {
     "method": "POST",
-    "url": "http://localhost:11434/v1/v1/chat/completions",
+    "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
     "headers": {},
     "body": {
       "model": "llama3.2:3b-instruct-fp16",
@@ -20,14 +20,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "chatcmpl-99",
+        "id": "chatcmpl-713",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I'd be happy to help you test the OpenAI 2 architecture!\n\nOpenAI 2 is a neural network model developed by OpenAI, and it's not exactly possible for me to directly \"test\" it. However, I can guide you through a simplified example of how to verify if OpenAI 2 has been implemented correctly in a specific codebase.\n\nHere's an outline of the steps:\n\n1. **Understand the basics**: Before we dive into testing, make sure you understand the architectural and functional details of OpenAI 2.\n2. **Get access to the model**: You'll need to obtain a trained OpenAI 2 model or implement it from scratch using a language like PyTorch or TensorFlow.\n3. **Implement a validation framework**: Create a simple validation framework that uses common tasks, such as classification on the GLUE benchmark, to evaluate the performance of your OpenAI 2 model.\n\nHere's a simplified code example in PyTorch:\n```python\nimport torch\nfrom transformers import AutoModelForSequenceClassification, AutoTokenizer\n\n# Load pre-trained OpenAI 2 Model(s)\nmodel_name = \"github/openai/OpenAIAccelerated-Text-To-Speech\"\nmodel_class = AutoModelForSequenceClassification\ntokenizer = AutoTokenizer.from_pretrained(model_name)\n\n# Initialize the model and tokenizer\nmodel = model_class(pretrained=True, num_labels=8)  # adjust label number according to your task\ntokenizer = tokenizer\n\ndef evaluate_model():\n    batch_size = 100\n    device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n\n    # Create a validation dataset from the GLUE benchmark\n    glue_datasets = [ datasets[\"glue\"][\"sst2\"], datasets[\"glue\"][\"mnli\"] ]\n    val_dataset = []\n    for i, gds in enumerate(glue_datasets):\n        data = gds[:10000]  # take only first few examples to speed up evaluation\n        input_ids = tokenizer encodings(data[\"sentence1\"], \n                                        attention_mask=data[\"attention_mask\"],\n                                        max_length=512,\n                                        padding=\"max_length\",\n                                        truncation=True,\n                                        return_tensors=\"pt\")\n\n        for example in data:\n            for sentence in [example['sentence1'], example['sentence2']]:\n                input_ids = input_ids.to(device)\n                outputs = model(input_ids, labels=None)  # adjust label to empty\n              \n\n    # Compute evaluation metrics\n    predictions = []\n    labels = []\n    accuracy = torch.zeros(8).to(device)\n\n    for sentence in data.values():\n        sentenceids = [input_ids[\"input_ids\"].flatten()]\n        _, pred_labels = model(sentenceids)\n        if len(predictions) == 0:\n            labels.extend([1, 2])\n        else:\n            assert len(labels)==len(sentences), 'error'\n            labels.append(preds[-1]) \n\n        # Append the prediction to the list\n        predictions.append(pred)\n\n    return accuracy\n\naccuracy = evaluate_model()\nprint(\"Accuracy:\", accuracy)\n```\n\nAfter running this code, you should get an estimate of the model's performance on the GLUE benchmark. Keep in mind that this is a simplified example and real-world openai 2 testing may require more involved validation processes.\n\nI hope this helps! Let me know if you have any further questions or if there are any specific areas where you'd like more information.",
+              "content": "I'd be happy to help you test the Transformer-XL (denoted as \"Test Trace OpenAI 2\") model, but first I need to clarify a few things:\n\n1. **Transformer-XL** is not an official name from OpenAI. It's actually a variant of the Transformer model proposed in the paper \"Long-Short Term Memory Are General: A Study on The Curvature of Time\" (2017) by Jinyu Chen, et al.\n2. **Trace OpenAI 2** sounds like a specific version or configuration of the Transformer-XL model, possibly developed by OpenAI.\n\nGiven these clarifications, I'll provide you with a general idea of how to test the Transformer-XL (or \"Test Trace OpenAI 2\") model using popular frameworks and libraries. Please note that this is not an exhaustive or definitive guide.\n\nTo test the Transformer-XL model, you can follow these steps:\n\n1. **Install the necessary dependencies**: You'll need a deep learning framework like TensorFlow or PyTorch, as well as a library for natural language processing (NLP) like Hugging Face's transformers.\n2. **Load the pre-trained weights**: You can use a pre-trained model checkpoint from Hugging Face's Transformers library or load your own weights trained on a specific task or dataset.\n3. **Prepare your data**: Load your text data into tokens, such as words or characters, and preprocess it according to the specific requirements of the Transformer-XL architecture (e.g., tokenization, padding, etc.).\n4. **Configure the model**: Adjust the hyperparameters to suit your specific test case, including the model's configuration, batch size, learning rate, etc.\n5. **Run the inference**: Use the loaded pre-trained weights to perform inference on your test data.\n\nHere's some sample Python code using PyTorch and Hugging Face's Transformers library to get you started:\n```python\nimport torch\nfrom transformers import LongformerForSequenceClassification, LongformerTokenizer\n\n# Load pre-trained weights\nmodel = LongformerForSequenceClassification.from_pretrained('test-trace-openai-2')\n\n# Prepare data\ntokenizer = model.tokenizer\ntext = \"This is a test sentence\"\ninputs = tokenizer(text, return_tensors='pt')\noutput = model(inputs['input_ids'], attention_mask=inputs['attention_mask'])\n\n# Print the results\nprint(output.logits)\n```\nPlease note that this code snippet is just an example and may not work as-is. You'll need to adapt it to your specific requirements and test data.\n\nKeep in mind that testing a model's performance on a specific task or dataset requires careful consideration of factors like:\n\n* **Test data quality**: Your test data should accurately represent the underlying distribution of your target dataset.\n* **Model evaluation metrics**: Choose relevant evaluation metrics that measure the model's performance on your specific task, such as accuracy, precision, recall, F1-score, etc.\n\nFeel free to ask if you have any further questions or need more guidance!",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -37,15 +37,15 @@
             }
           }
         ],
-        "created": 1754510064,
+        "created": 1756921250,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "chat.completion",
         "service_tier": null,
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 694,
+          "completion_tokens": 614,
           "prompt_tokens": 31,
-          "total_tokens": 725,
+          "total_tokens": 645,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }

tests/integration/recordings/responses/836f51dfb3c5.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:14:03.770002Z",
+        "created_at": "2025-09-03T17:37:51.562847Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 395965875,
-        "load_duration": 178888708,
+        "total_duration": 272296250,
+        "load_duration": 131747125,
         "prompt_eval_count": 214,
-        "prompt_eval_duration": 170000000,
+        "prompt_eval_duration": 124006709,
         "eval_count": 2,
-        "eval_duration": 44000000,
+        "eval_duration": 15572291,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/840fbb380b73.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:13:57.935921Z",
+        "created_at": "2025-09-03T17:37:47.871962Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 313787333,
-        "load_duration": 89797542,
+        "total_duration": 301629042,
+        "load_duration": 102832917,
         "prompt_eval_count": 233,
-        "prompt_eval_duration": 167000000,
+        "prompt_eval_duration": 154806625,
         "eval_count": 5,
-        "eval_duration": 55000000,
+        "eval_duration": 43361542,
         "response": "unsafe\nS1",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/85594a69d74a.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:12:54.634929Z",
+        "created_at": "2025-09-03T17:37:36.046489Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 233222375,
-        "load_duration": 136303125,
+        "total_duration": 198969250,
+        "load_duration": 110421000,
         "prompt_eval_count": 213,
-        "prompt_eval_duration": 78000000,
+        "prompt_eval_duration": 76196541,
         "eval_count": 2,
-        "eval_duration": 17000000,
+        "eval_duration": 11832042,
         "response": "safe",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/8752115f8d0c.json

@@ -0,0 +1,71 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://shan-mfbb618r-eastus2.cognitiveservices.azure.com/openai/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "gpt-5-mini",
+      "messages": [
+        {
+          "role": "user",
+          "content": "Hello, world!"
+        }
+      ],
+      "stream": false
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "gpt-5-mini"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.chat.chat_completion.ChatCompletion",
+      "__data__": {
+        "id": "chatcmpl-CECIuyylsMNXspa83k8LrD8SQadNY",
+        "choices": [
+          {
+            "finish_reason": "stop",
+            "index": 0,
+            "logprobs": null,
+            "message": {
+              "content": "Hello! \ud83d\udc4b How can I help you today \u2014 answer a question, write or edit something, debug code, brainstorm ideas, or anything else?",
+              "refusal": null,
+              "role": "assistant",
+              "annotations": [],
+              "audio": null,
+              "function_call": null,
+              "tool_calls": null
+            },
+            "content_filter_results": {}
+          }
+        ],
+        "created": 1757499924,
+        "model": "gpt-5-mini-2025-08-07",
+        "object": "chat.completion",
+        "service_tier": null,
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 40,
+          "prompt_tokens": 10,
+          "total_tokens": 50,
+          "completion_tokens_details": {
+            "accepted_prediction_tokens": 0,
+            "audio_tokens": 0,
+            "reasoning_tokens": 0,
+            "rejected_prediction_tokens": 0
+          },
+          "prompt_tokens_details": {
+            "audio_tokens": 0,
+            "cached_tokens": 0
+          }
+        },
+        "prompt_filter_results": [
+          {
+            "prompt_index": 0,
+            "content_filter_results": {}
+          }
+        ]
+      }
+    },
+    "is_streaming": false
+  }
+}

tests/integration/recordings/responses/894fdacb1cfa.json

@@ -0,0 +1,176 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/chat/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "messages": [
+        {
+          "role": "user",
+          "content": "What's the weather in Tokyo? Use the get_weather function to get the weather."
+        }
+      ],
+      "stream": true,
+      "tools": [
+        {
+          "type": "function",
+          "function": {
+            "name": "get_weather",
+            "description": "Get the weather in a given city",
+            "parameters": {
+              "type": "object",
+              "properties": {
+                "city": {
+                  "type": "string",
+                  "description": "The city to get the weather for"
+                }
+              }
+            }
+          }
+        }
+      ]
+    },
+    "endpoint": "/v1/chat/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": [
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtX7R-62bZhn-9801a22f6ad243dc",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 1758039022,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtX7R-62bZhn-9801a22f6ad243dc",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": "call_jy63yt7kp8hfof3sy4pim94o",
+                    "function": {
+                      "arguments": "",
+                      "name": "get_weather"
+                    },
+                    "type": "function"
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 1758039022,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtX7R-62bZhn-9801a22f6ad243dc",
+          "choices": [
+            {
+              "delta": {
+                "content": null,
+                "function_call": null,
+                "refusal": null,
+                "role": null,
+                "tool_calls": [
+                  {
+                    "index": 0,
+                    "id": null,
+                    "function": {
+                      "arguments": "{\"city\":\"Tokyo\"}",
+                      "name": null
+                    },
+                    "type": null
+                  }
+                ]
+              },
+              "finish_reason": null,
+              "index": 0,
+              "logprobs": null
+            }
+          ],
+          "created": 1758039022,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": null
+        }
+      },
+      {
+        "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk",
+        "__data__": {
+          "id": "oBUtX7R-62bZhn-9801a22f6ad243dc",
+          "choices": [
+            {
+              "delta": {
+                "content": "",
+                "function_call": null,
+                "refusal": null,
+                "role": "assistant",
+                "tool_calls": null,
+                "token_id": 128008
+              },
+              "finish_reason": "tool_calls",
+              "index": 0,
+              "logprobs": null,
+              "text": "",
+              "seed": 1489065696184500700
+            }
+          ],
+          "created": 1758039022,
+          "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+          "object": "chat.completion.chunk",
+          "service_tier": null,
+          "system_fingerprint": null,
+          "usage": {
+            "completion_tokens": 24,
+            "prompt_tokens": 193,
+            "total_tokens": 217,
+            "completion_tokens_details": null,
+            "prompt_tokens_details": null,
+            "cached_tokens": 0
+          }
+        }
+      }
+    ],
+    "is_streaming": true
+  }
+}

tests/integration/recordings/responses/97d3812bfccb.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:14:06.082832Z",
+        "created_at": "2025-09-03T17:37:52.965106Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 421905083,
-        "load_duration": 88557750,
+        "total_duration": 376594792,
+        "load_duration": 158273792,
         "prompt_eval_count": 217,
-        "prompt_eval_duration": 278000000,
+        "prompt_eval_duration": 177001375,
         "eval_count": 5,
-        "eval_duration": 54000000,
+        "eval_duration": 40927500,
         "response": "unsafe\nS1",
         "thinking": null,
         "context": null

tests/integration/recordings/responses/97e259c0d3e5.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.138696Z",
+          "created_at": "2025-09-03T17:37:53.505006Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.195013Z",
+          "created_at": "2025-09-03T17:37:53.547032Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.246591Z",
+          "created_at": "2025-09-03T17:37:53.588985Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.29736Z",
+          "created_at": "2025-09-03T17:37:53.631139Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.347941Z",
+          "created_at": "2025-09-03T17:37:53.67269Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.399151Z",
+          "created_at": "2025-09-03T17:37:53.714798Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.452488Z",
+          "created_at": "2025-09-03T17:37:53.756492Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.50538Z",
+          "created_at": "2025-09-03T17:37:53.798115Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.558656Z",
+          "created_at": "2025-09-03T17:37:53.840012Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.610408Z",
+          "created_at": "2025-09-03T17:37:53.882555Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.66358Z",
+          "created_at": "2025-09-03T17:37:53.924566Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.717638Z",
+          "created_at": "2025-09-03T17:37:53.966279Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,7 +238,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.769423Z",
+          "created_at": "2025-09-03T17:37:54.008483Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -256,7 +256,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.819395Z",
+          "created_at": "2025-09-03T17:37:54.050042Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -274,7 +274,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.871391Z",
+          "created_at": "2025-09-03T17:37:54.092416Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -292,7 +292,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.924892Z",
+          "created_at": "2025-09-03T17:37:54.134857Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -310,7 +310,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:07.976557Z",
+          "created_at": "2025-09-03T17:37:54.176408Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -328,7 +328,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:08.029579Z",
+          "created_at": "2025-09-03T17:37:54.217553Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -346,15 +346,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:08.082749Z",
+          "created_at": "2025-09-03T17:37:54.259141Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1425800209,
-          "load_duration": 138858459,
+          "total_duration": 1008303875,
+          "load_duration": 119709875,
           "prompt_eval_count": 384,
-          "prompt_eval_duration": 340000000,
+          "prompt_eval_duration": 132645959,
           "eval_count": 19,
-          "eval_duration": 945000000,
+          "eval_duration": 755215708,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/9c140a29ae09.json

@@ -22,7 +22,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:09.83858Z",
+          "created_at": "2025-09-03T17:37:55.13567Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -40,7 +40,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:09.891488Z",
+          "created_at": "2025-09-03T17:37:55.17774Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -58,7 +58,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:09.945656Z",
+          "created_at": "2025-09-03T17:37:55.220061Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -76,7 +76,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:09.996898Z",
+          "created_at": "2025-09-03T17:37:55.261406Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -94,7 +94,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.053632Z",
+          "created_at": "2025-09-03T17:37:55.302615Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -112,7 +112,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.105753Z",
+          "created_at": "2025-09-03T17:37:55.343879Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -130,7 +130,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.157953Z",
+          "created_at": "2025-09-03T17:37:55.384951Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -148,7 +148,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.210869Z",
+          "created_at": "2025-09-03T17:37:55.426563Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -166,7 +166,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.263387Z",
+          "created_at": "2025-09-03T17:37:55.467648Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -184,7 +184,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.317794Z",
+          "created_at": "2025-09-03T17:37:55.509469Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -202,7 +202,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.373978Z",
+          "created_at": "2025-09-03T17:37:55.552302Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -220,7 +220,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.429702Z",
+          "created_at": "2025-09-03T17:37:55.596236Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -238,15 +238,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-08-01T23:14:10.483762Z",
+          "created_at": "2025-09-03T17:37:55.637816Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 1041142084,
-          "load_duration": 110407459,
+          "total_duration": 726849208,
+          "load_duration": 147625750,
           "prompt_eval_count": 415,
-          "prompt_eval_duration": 283000000,
+          "prompt_eval_duration": 75722709,
           "eval_count": 13,
-          "eval_duration": 646000000,
+          "eval_duration": 502787333,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/9c28ec9ac338.json

@@ -21,7 +21,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.316207Z",
+          "created_at": "2025-09-03T17:34:23.434819Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -39,7 +39,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.358611Z",
+          "created_at": "2025-09-03T17:34:23.477986Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -57,7 +57,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.401272Z",
+          "created_at": "2025-09-03T17:34:23.520282Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -75,7 +75,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.444321Z",
+          "created_at": "2025-09-03T17:34:23.561947Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -93,7 +93,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.48795Z",
+          "created_at": "2025-09-03T17:34:23.603986Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -111,7 +111,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.530158Z",
+          "created_at": "2025-09-03T17:34:23.646447Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -129,7 +129,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.573318Z",
+          "created_at": "2025-09-03T17:34:23.688452Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -147,7 +147,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.616297Z",
+          "created_at": "2025-09-03T17:34:23.730147Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -165,7 +165,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.659527Z",
+          "created_at": "2025-09-03T17:34:23.772004Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -183,7 +183,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.702422Z",
+          "created_at": "2025-09-03T17:34:23.813913Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -201,7 +201,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.745894Z",
+          "created_at": "2025-09-03T17:34:23.856Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -219,7 +219,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.788811Z",
+          "created_at": "2025-09-03T17:34:23.897939Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -237,7 +237,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.831618Z",
+          "created_at": "2025-09-03T17:34:23.939953Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -255,7 +255,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.874469Z",
+          "created_at": "2025-09-03T17:34:23.982033Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -273,7 +273,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.917372Z",
+          "created_at": "2025-09-03T17:34:24.026067Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -291,7 +291,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:36.960558Z",
+          "created_at": "2025-09-03T17:34:24.069083Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -309,7 +309,7 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:37.004223Z",
+          "created_at": "2025-09-03T17:34:24.112349Z",
           "done": false,
           "done_reason": null,
           "total_duration": null,
@@ -327,15 +327,15 @@
         "__type__": "ollama._types.GenerateResponse",
         "__data__": {
           "model": "llama3.2:3b-instruct-fp16",
-          "created_at": "2025-07-29T23:46:37.046563Z",
+          "created_at": "2025-09-03T17:34:24.155424Z",
           "done": true,
           "done_reason": "stop",
-          "total_duration": 845522667,
-          "load_duration": 47784875,
+          "total_duration": 896931125,
+          "load_duration": 89697291,
           "prompt_eval_count": 511,
-          "prompt_eval_duration": 66135292,
+          "prompt_eval_duration": 83876750,
           "eval_count": 18,
-          "eval_duration": 730999291,
+          "eval_duration": 722156292,
           "response": "",
           "thinking": null,
           "context": null

tests/integration/recordings/responses/9e7a83d3d596.json

@@ -15,23 +15,23 @@
     "body": {
       "__type__": "openai.types.completion.Completion",
       "__data__": {
-        "id": "cmpl-43",
+        "id": "cmpl-775",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
-            "text": "Blue.\n\nMy response is based on the traditional English rhyme that pairs the colors of roses (red) with violets in a poetic and somewhat whimsical way. This specific version of the rhyme goes like this:\n\n\"Roses are red,\nViolets are blue,\nSugar is sweet,\nAnd so are you.\"\n\nIn modern times, variations of this rhyme can deviate from the original \"blue\" for violets, but in my complete sentence as requested, sticking with a widely recognized completion adds an air of timelessness and familiarity to the phrase."
+            "text": "Blue.\n\nMy response is based on the traditional rhyme \"Roses are Red, Violets are Blue,\" which is a well-known poem or phrase often used as a greeting or way to express affection. The exact wording may vary slightly depending on the source, but the general meaning remains the same: violets are typically depicted as blue-colored flowers in this rhyme."
           }
         ],
-        "created": 1754348148,
+        "created": 1756921025,
         "model": "llama3.2:3b-instruct-fp16",
         "object": "text_completion",
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 113,
+          "completion_tokens": 75,
           "prompt_tokens": 50,
-          "total_tokens": 163,
+          "total_tokens": 125,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }

tests/integration/recordings/responses/9fadf5a3d68f.json

@@ -20,15 +20,15 @@
       "__type__": "ollama._types.GenerateResponse",
       "__data__": {
         "model": "llama-guard3:1b",
-        "created_at": "2025-08-01T23:14:22.168612Z",
+        "created_at": "2025-09-03T17:38:03.270261Z",
         "done": true,
         "done_reason": "stop",
-        "total_duration": 198446125,
-        "load_duration": 31859666,
+        "total_duration": 244051875,
+        "load_duration": 111239500,
         "prompt_eval_count": 224,
-        "prompt_eval_duration": 151000000,
+        "prompt_eval_duration": 120962791,
         "eval_count": 2,
-        "eval_duration": 13000000,
+        "eval_duration": 11306292,
         "response": "safe",
         "thinking": null,
         "context": null