fix: keep stopwords updated

2026-01-09 14:37:59 -05:00 · 2025-11-06 21:10:25 -05:00
parent 6f36d7003b
commit 40a2d387a1
8 changed files with 418 additions and 6 deletions
--- a/lib/crewai/src/crewai/llms/hooks/transport.py
+++ b/lib/crewai/src/crewai/llms/hooks/transport.py
@@ -25,7 +25,7 @@ if TYPE_CHECKING:
    from crewai.llms.hooks.base import BaseInterceptor


-class HTTPTransportKwargs(TypedDict):
+class HTTPTransportKwargs(TypedDict, total=False):
    """Typed dictionary for httpx.HTTPTransport initialization parameters.

    These parameters configure the underlying HTTP transport behavior including
@@ -33,14 +33,14 @@ class HTTPTransportKwargs(TypedDict):
    """

    verify: bool | str | SSLContext
-    cert: NotRequired[CertTypes | None]
+    cert: NotRequired[CertTypes]
    trust_env: bool
    http1: bool
    http2: bool
    limits: Limits
-    proxy: NotRequired[ProxyTypes | None]
-    uds: NotRequired[str | None]
-    local_address: NotRequired[str | None]
+    proxy: NotRequired[ProxyTypes]
+    uds: NotRequired[str]
+    local_address: NotRequired[str]
    retries: int
    socket_options: NotRequired[
        Iterable[
@@ -48,7 +48,6 @@ class HTTPTransportKwargs(TypedDict):
            | tuple[int, int, bytes | bytearray]
            | tuple[int, int, None, int]
        ]
-        | None
    ]


--- a/lib/crewai/src/crewai/llms/providers/anthropic/completion.py
+++ b/lib/crewai/src/crewai/llms/providers/anthropic/completion.py
@@ -94,6 +94,30 @@ class AnthropicCompletion(BaseLLM):
        self.is_claude_3 = "claude-3" in model.lower()
        self.supports_tools = self.is_claude_3  # Claude 3+ supports tool use

+    @property
+    def stop(self) -> list[str]:
+        """Get stop sequences sent to the API."""
+        return self.stop_sequences
+
+    @stop.setter
+    def stop(self, value: list[str] | str | None) -> None:
+        """Set stop sequences.
+
+        Synchronizes stop_sequences to ensure values set by CrewAgentExecutor
+        are properly sent to the Anthropic API.
+
+        Args:
+            value: Stop sequences as a list, single string, or None
+        """
+        if value is None:
+            self.stop_sequences = []
+        elif isinstance(value, str):
+            self.stop_sequences = [value]
+        elif isinstance(value, list):
+            self.stop_sequences = value
+        else:
+            self.stop_sequences = []
+
    def _get_client_params(self) -> dict[str, Any]:
        """Get client parameters."""

--- a/lib/crewai/src/crewai/llms/providers/bedrock/completion.py
+++ b/lib/crewai/src/crewai/llms/providers/bedrock/completion.py
@@ -243,6 +243,30 @@ class BedrockCompletion(BaseLLM):
        # Handle inference profiles for newer models
        self.model_id = model

+    @property
+    def stop(self) -> list[str]:
+        """Get stop sequences sent to the API."""
+        return list(self.stop_sequences)
+
+    @stop.setter
+    def stop(self, value: Sequence[str] | str | None) -> None:
+        """Set stop sequences.
+
+        Synchronizes stop_sequences to ensure values set by CrewAgentExecutor
+        are properly sent to the Bedrock API.
+
+        Args:
+            value: Stop sequences as a Sequence, single string, or None
+        """
+        if value is None:
+            self.stop_sequences = []
+        elif isinstance(value, str):
+            self.stop_sequences = [value]
+        elif isinstance(value, Sequence):
+            self.stop_sequences = list(value)
+        else:
+            self.stop_sequences = []
+
    def call(
        self,
        messages: str | list[LLMMessage],
--- a/lib/crewai/src/crewai/llms/providers/gemini/completion.py
+++ b/lib/crewai/src/crewai/llms/providers/gemini/completion.py
@@ -104,6 +104,30 @@ class GeminiCompletion(BaseLLM):
        self.is_gemini_1_5 = "gemini-1.5" in model.lower()
        self.supports_tools = self.is_gemini_1_5 or self.is_gemini_2

+    @property
+    def stop(self) -> list[str]:
+        """Get stop sequences sent to the API."""
+        return self.stop_sequences
+
+    @stop.setter
+    def stop(self, value: list[str] | str | None) -> None:
+        """Set stop sequences.
+
+        Synchronizes stop_sequences to ensure values set by CrewAgentExecutor
+        are properly sent to the Gemini API.
+
+        Args:
+            value: Stop sequences as a list, single string, or None
+        """
+        if value is None:
+            self.stop_sequences = []
+        elif isinstance(value, str):
+            self.stop_sequences = [value]
+        elif isinstance(value, list):
+            self.stop_sequences = value
+        else:
+            self.stop_sequences = []
+
    def _initialize_client(self, use_vertexai: bool = False) -> genai.Client:  # type: ignore[no-any-unimported]
        """Initialize the Google Gen AI client with proper parameter handling.

--- a/lib/crewai/tests/cassettes/test_anthropic_stop_sequences_sent_to_api.yaml
+++ b/lib/crewai/tests/cassettes/test_anthropic_stop_sequences_sent_to_api.yaml
@@ -0,0 +1,202 @@
+interactions:
+- request:
+    body: '{"trace_id": "1703c4e0-d3be-411c-85e7-48018c2df384", "execution_type":
+      "crew", "user_identifier": null, "execution_context": {"crew_fingerprint": null,
+      "crew_name": "Unknown Crew", "flow_name": null, "crewai_version": "1.3.0", "privacy_level":
+      "standard"}, "execution_metadata": {"expected_duration_estimate": 300, "agent_count":
+      0, "task_count": 0, "flow_method_count": 0, "execution_started_at": "2025-11-07T01:58:22.260309+00:00"}}'
+    headers:
+      Accept:
+      - '*/*'
+      Accept-Encoding:
+      - gzip, deflate, zstd
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '434'
+      Content-Type:
+      - application/json
+      User-Agent:
+      - CrewAI-CLI/1.3.0
+      X-Crewai-Version:
+      - 1.3.0
+    method: POST
+    uri: https://app.crewai.com/crewai_plus/api/v1/tracing/batches
+  response:
+    body:
+      string: '{"error":"bad_credentials","message":"Bad credentials"}'
+    headers:
+      Connection:
+      - keep-alive
+      Content-Length:
+      - '55'
+      Content-Type:
+      - application/json; charset=utf-8
+      Date:
+      - Fri, 07 Nov 2025 01:58:22 GMT
+      cache-control:
+      - no-store
+      content-security-policy:
+      - 'default-src ''self'' *.app.crewai.com app.crewai.com; script-src ''self''
+        ''unsafe-inline'' *.app.crewai.com app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts
+        https://www.gstatic.com https://run.pstmn.io https://apis.google.com https://apis.google.com/js/api.js
+        https://accounts.google.com https://accounts.google.com/gsi/client https://cdnjs.cloudflare.com/ajax/libs/normalize/8.0.1/normalize.min.css.map
+        https://*.google.com https://docs.google.com https://slides.google.com https://js.hs-scripts.com
+        https://js.sentry-cdn.com https://browser.sentry-cdn.com https://www.googletagmanager.com
+        https://js-na1.hs-scripts.com https://js.hubspot.com http://js-na1.hs-scripts.com
+        https://bat.bing.com https://cdn.amplitude.com https://cdn.segment.com https://d1d3n03t5zntha.cloudfront.net/
+        https://descriptusercontent.com https://edge.fullstory.com https://googleads.g.doubleclick.net
+        https://js.hs-analytics.net https://js.hs-banner.com https://js.hsadspixel.net
+        https://js.hscollectedforms.net https://js.usemessages.com https://snap.licdn.com
+        https://static.cloudflareinsights.com https://static.reo.dev https://www.google-analytics.com
+        https://share.descript.com/; style-src ''self'' ''unsafe-inline'' *.app.crewai.com
+        app.crewai.com https://cdn.jsdelivr.net/npm/apexcharts; img-src ''self'' data:
+        *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com https://dashboard.tools.crewai.com
+        https://cdn.jsdelivr.net https://forms.hsforms.com https://track.hubspot.com
+        https://px.ads.linkedin.com https://px4.ads.linkedin.com https://www.google.com
+        https://www.google.com.br; font-src ''self'' data: *.app.crewai.com app.crewai.com;
+        connect-src ''self'' *.app.crewai.com app.crewai.com https://zeus.tools.crewai.com
+        https://connect.useparagon.com/ https://zeus.useparagon.com/* https://*.useparagon.com/*
+        https://run.pstmn.io https://connect.tools.crewai.com/ https://*.sentry.io
+        https://www.google-analytics.com https://edge.fullstory.com https://rs.fullstory.com
+        https://api.hubspot.com https://forms.hscollectedforms.net https://api.hubapi.com
+        https://px.ads.linkedin.com https://px4.ads.linkedin.com https://google.com/pagead/form-data/16713662509
+        https://google.com/ccm/form-data/16713662509 https://www.google.com/ccm/collect
+        https://worker-actionkit.tools.crewai.com https://api.reo.dev; frame-src ''self''
+        *.app.crewai.com app.crewai.com https://connect.useparagon.com/ https://zeus.tools.crewai.com
+        https://zeus.useparagon.com/* https://connect.tools.crewai.com/ https://docs.google.com
+        https://drive.google.com https://slides.google.com https://accounts.google.com
+        https://*.google.com https://app.hubspot.com/ https://td.doubleclick.net https://www.googletagmanager.com/
+        https://www.youtube.com https://share.descript.com'
+      expires:
+      - '0'
+      permissions-policy:
+      - camera=(), microphone=(self), geolocation=()
+      pragma:
+      - no-cache
+      referrer-policy:
+      - strict-origin-when-cross-origin
+      strict-transport-security:
+      - max-age=63072000; includeSubDomains
+      vary:
+      - Accept
+      x-content-type-options:
+      - nosniff
+      x-frame-options:
+      - SAMEORIGIN
+      x-permitted-cross-domain-policies:
+      - none
+      x-request-id:
+      - 4124c4ce-02cf-4d08-9b0b-8983c2e9da6e
+      x-runtime:
+      - '0.073764'
+      x-xss-protection:
+      - 1; mode=block
+    status:
+      code: 401
+      message: Unauthorized
+- request:
+    body: '{"max_tokens":4096,"messages":[{"role":"user","content":"Say hello in one
+      word"}],"model":"claude-3-5-haiku-20241022","stop_sequences":["\nObservation:","\nThought:"],"stream":false}'
+    headers:
+      accept:
+      - application/json
+      accept-encoding:
+      - gzip, deflate, zstd
+      anthropic-version:
+      - '2023-06-01'
+      connection:
+      - keep-alive
+      content-length:
+      - '182'
+      content-type:
+      - application/json
+      host:
+      - api.anthropic.com
+      user-agent:
+      - Anthropic/Python 0.71.0
+      x-stainless-arch:
+      - arm64
+      x-stainless-async:
+      - 'false'
+      x-stainless-lang:
+      - python
+      x-stainless-os:
+      - MacOS
+      x-stainless-package-version:
+      - 0.71.0
+      x-stainless-retry-count:
+      - '0'
+      x-stainless-runtime:
+      - CPython
+      x-stainless-runtime-version:
+      - 3.12.9
+      x-stainless-timeout:
+      - NOT_GIVEN
+    method: POST
+    uri: https://api.anthropic.com/v1/messages
+  response:
+    body:
+      string: !!binary |
+        H4sIAAAAAAAAAwAAAP//dJBdS8QwEEX/y31Ope26u5J3dwWfBH0SCTEZtmHTpCYTXSn979LF4hc+
+        DdxzZgbuiD5a8pAwXhdL1apaV512x1K1dXvZ1G0LAWch0eeDqpvN1f3q7bTPz91tc/ewLcfr/Xaz
+        gwC/DzRblLM+EARS9HOgc3aZdWAImBiYAkM+jovPdJrJeUjckPfxAtOTQOY4qEQ6xwAJClZxSQGf
+        INNLoWAIMhTvBcr5qRzhwlBYcTxSyJBNK2C06UiZRJpdDOqnUC88kbb/sWV3vk9DRz0l7dW6/+t/
+        0ab7TSeBWPh7tBbIlF6dIcWOEiTmoqxOFtP0AQAA//8DAM5WvkqaAQAA
+    headers:
+      CF-RAY:
+      - 99a939a5a931556e-EWR
+      Connection:
+      - keep-alive
+      Content-Encoding:
+      - gzip
+      Content-Type:
+      - application/json
+      Date:
+      - Fri, 07 Nov 2025 01:58:22 GMT
+      Server:
+      - cloudflare
+      Transfer-Encoding:
+      - chunked
+      X-Robots-Tag:
+      - none
+      anthropic-organization-id:
+      - SCRUBBED-ORG-ID
+      anthropic-ratelimit-input-tokens-limit:
+      - '400000'
+      anthropic-ratelimit-input-tokens-remaining:
+      - '400000'
+      anthropic-ratelimit-input-tokens-reset:
+      - '2025-11-07T01:58:22Z'
+      anthropic-ratelimit-output-tokens-limit:
+      - '80000'
+      anthropic-ratelimit-output-tokens-remaining:
+      - '80000'
+      anthropic-ratelimit-output-tokens-reset:
+      - '2025-11-07T01:58:22Z'
+      anthropic-ratelimit-requests-limit:
+      - '4000'
+      anthropic-ratelimit-requests-remaining:
+      - '3999'
+      anthropic-ratelimit-requests-reset:
+      - '2025-11-07T01:58:22Z'
+      anthropic-ratelimit-tokens-limit:
+      - '480000'
+      anthropic-ratelimit-tokens-remaining:
+      - '480000'
+      anthropic-ratelimit-tokens-reset:
+      - '2025-11-07T01:58:22Z'
+      cf-cache-status:
+      - DYNAMIC
+      request-id:
+      - req_011CUshbL7CEVoner91hUvxL
+      retry-after:
+      - '41'
+      strict-transport-security:
+      - max-age=31536000; includeSubDomains; preload
+      x-envoy-upstream-service-time:
+      - '390'
+    status:
+      code: 200
+      message: OK
+version: 1
--- a/lib/crewai/tests/llms/anthropic/test_anthropic.py
+++ b/lib/crewai/tests/llms/anthropic/test_anthropic.py
@@ -664,3 +664,37 @@ def test_anthropic_token_usage_tracking():
        assert usage["input_tokens"] == 50
        assert usage["output_tokens"] == 25
        assert usage["total_tokens"] == 75
+
+
+def test_anthropic_stop_sequences_sync():
+    """Test that stop and stop_sequences attributes stay synchronized."""
+    llm = LLM(model="anthropic/claude-3-5-sonnet-20241022")
+
+    # Test setting stop as a list
+    llm.stop = ["\nObservation:", "\nThought:"]
+    assert llm.stop_sequences == ["\nObservation:", "\nThought:"]
+    assert llm.stop == ["\nObservation:", "\nThought:"]
+
+    # Test setting stop as a string
+    llm.stop = "\nFinal Answer:"
+    assert llm.stop_sequences == ["\nFinal Answer:"]
+    assert llm.stop == ["\nFinal Answer:"]
+
+    # Test setting stop as None
+    llm.stop = None
+    assert llm.stop_sequences == []
+    assert llm.stop == []
+
+
+@pytest.mark.vcr(filter_headers=["authorization", "x-api-key"])
+def test_anthropic_stop_sequences_sent_to_api():
+    """Test that stop_sequences are properly sent to the Anthropic API."""
+    llm = LLM(model="anthropic/claude-3-5-haiku-20241022")
+
+    llm.stop = ["\nObservation:", "\nThought:"]
+
+    result = llm.call("Say hello in one word")
+
+    assert result is not None
+    assert isinstance(result, str)
+    assert len(result) > 0
--- a/lib/crewai/tests/llms/bedrock/test_bedrock.py
+++ b/lib/crewai/tests/llms/bedrock/test_bedrock.py
@@ -736,3 +736,56 @@ def test_bedrock_client_error_handling():
        with pytest.raises(RuntimeError) as exc_info:
            llm.call("Hello")
        assert "throttled" in str(exc_info.value).lower()
+
+
+def test_bedrock_stop_sequences_sync():
+    """Test that stop and stop_sequences attributes stay synchronized."""
+    llm = LLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
+
+    # Test setting stop as a list
+    llm.stop = ["\nObservation:", "\nThought:"]
+    assert list(llm.stop_sequences) == ["\nObservation:", "\nThought:"]
+    assert llm.stop == ["\nObservation:", "\nThought:"]
+
+    # Test setting stop as a string
+    llm.stop = "\nFinal Answer:"
+    assert list(llm.stop_sequences) == ["\nFinal Answer:"]
+    assert llm.stop == ["\nFinal Answer:"]
+
+    # Test setting stop as None
+    llm.stop = None
+    assert list(llm.stop_sequences) == []
+    assert llm.stop == []
+
+
+def test_bedrock_stop_sequences_sent_to_api():
+    """Test that stop_sequences are properly sent to the Bedrock API."""
+    llm = LLM(model="bedrock/anthropic.claude-3-5-sonnet-20241022-v2:0")
+
+    # Set stop sequences via the stop attribute (simulating CrewAgentExecutor)
+    llm.stop = ["\nObservation:", "\nThought:"]
+
+    # Patch the API call to capture parameters without making real call
+    with patch.object(llm.client, 'converse') as mock_converse:
+        mock_response = {
+            'output': {
+                'message': {
+                    'role': 'assistant',
+                    'content': [{'text': 'Hello'}]
+                }
+            },
+            'usage': {
+                'inputTokens': 10,
+                'outputTokens': 5,
+                'totalTokens': 15
+            }
+        }
+        mock_converse.return_value = mock_response
+
+        llm.call("Say hello in one word")
+
+        # Verify stop_sequences were passed to the API in the inference config
+        call_kwargs = mock_converse.call_args[1]
+        assert "inferenceConfig" in call_kwargs
+        assert "stopSequences" in call_kwargs["inferenceConfig"]
+        assert call_kwargs["inferenceConfig"]["stopSequences"] == ["\nObservation:", "\nThought:"]
--- a/lib/crewai/tests/llms/google/test_google.py
+++ b/lib/crewai/tests/llms/google/test_google.py
@@ -648,3 +648,55 @@ def test_gemini_token_usage_tracking():
        assert usage["candidates_token_count"] == 25
        assert usage["total_token_count"] == 75
        assert usage["total_tokens"] == 75
+
+
+def test_gemini_stop_sequences_sync():
+    """Test that stop and stop_sequences attributes stay synchronized."""
+    llm = LLM(model="google/gemini-2.0-flash-001")
+
+    # Test setting stop as a list
+    llm.stop = ["\nObservation:", "\nThought:"]
+    assert llm.stop_sequences == ["\nObservation:", "\nThought:"]
+    assert llm.stop == ["\nObservation:", "\nThought:"]
+
+    # Test setting stop as a string
+    llm.stop = "\nFinal Answer:"
+    assert llm.stop_sequences == ["\nFinal Answer:"]
+    assert llm.stop == ["\nFinal Answer:"]
+
+    # Test setting stop as None
+    llm.stop = None
+    assert llm.stop_sequences == []
+    assert llm.stop == []
+
+
+def test_gemini_stop_sequences_sent_to_api():
+    """Test that stop_sequences are properly sent to the Gemini API."""
+    llm = LLM(model="google/gemini-2.0-flash-001")
+
+    # Set stop sequences via the stop attribute (simulating CrewAgentExecutor)
+    llm.stop = ["\nObservation:", "\nThought:"]
+
+    # Patch the API call to capture parameters without making real call
+    with patch.object(llm.client.models, 'generate_content') as mock_generate:
+        mock_response = MagicMock()
+        mock_response.text = "Hello"
+        mock_response.candidates = []
+        mock_response.usage_metadata = MagicMock(
+            prompt_token_count=10,
+            candidates_token_count=5,
+            total_token_count=15
+        )
+        mock_generate.return_value = mock_response
+
+        llm.call("Say hello in one word")
+
+        # Verify stop_sequences were passed to the API in the config
+        call_kwargs = mock_generate.call_args[1]
+        assert "config" in call_kwargs
+        # The config object should have stop_sequences set
+        config = call_kwargs["config"]
+        # Check if the config has stop_sequences attribute
+        assert hasattr(config, 'stop_sequences') or 'stop_sequences' in config.__dict__
+        if hasattr(config, 'stop_sequences'):
+            assert config.stop_sequences == ["\nObservation:", "\nThought:"]