github-haystack 1.1.0__py3-none-any.whl → 1.2.1__py3-none-any.whl

{github_haystack-1.1.0.dist-info → github_haystack-1.2.1.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: github-haystack
-Version: 1.1.0
+Version: 1.2.1
 Summary: Haystack components for interacting with GitHub repositories
 Project-URL: Source, https://github.com/deepset-ai/haystack-core-integrations/github
 Project-URL: Documentation, https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/github/README.md
@@ -27,19 +27,10 @@ Description-Content-Type: text/markdown
 [![PyPI - Version](https://img.shields.io/pypi/v/github-haystack.svg)](https://pypi.org/project/github-haystack)
 [![PyPI - Python Version](https://img.shields.io/pypi/pyversions/github-haystack.svg)](https://pypi.org/project/github-haystack)
 
------
+- [Integration page](https://haystack.deepset.ai/integrations/github)
+- [Changelog](https://github.com/deepset-ai/haystack-core-integrations/blob/main/integrations/github/CHANGELOG.md)
+ 
+---
+## Contributing
 
-## Table of Contents
-
-- [Installation](#installation)
-- [License](#license)
-
-## Installation
-
-```console
-pip install github-haystack
-```
-
-## License
-
-`github-haystack` is distributed under the terms of the [Apache-2.0](https://spdx.org/licenses/Apache-2.0.html) license.
+Refer to the general [Contribution Guidelines](https://github.com/deepset-ai/haystack-core-integrations/blob/main/CONTRIBUTING.md).

{github_haystack-1.1.0.dist-info → github_haystack-1.2.1.dist-info}/RECORD

@@ -1,29 +1,31 @@
 haystack_integrations/components/connectors/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
 haystack_integrations/components/connectors/github/__init__.py,sha256=aRIkCcJ_ogsyt67cwjZQu8rqP7yIQu8jRzK6TAYRGx4,557
-haystack_integrations/components/connectors/github/file_editor.py,sha256=DbW57Ztm9kv8mCYSJGhUY7xp9wXOvRdhomOosNbBFnQ,11738
-haystack_integrations/components/connectors/github/issue_commenter.py,sha256=S8VhaPaIQJ29TJNMsnfPns4lNBNAnC0QUxuktKTrnfE,5618
-haystack_integrations/components/connectors/github/issue_viewer.py,sha256=Xionw1Y8jGxMCo2AXDUjqWk_yaJTW0d9xhvSr8bOGcM,7368
-haystack_integrations/components/connectors/github/pr_creator.py,sha256=KEWgXVQlLjaSJiwqn-5vIxOCG1PHH8OKEJtNphI3o_g,11428
-haystack_integrations/components/connectors/github/repo_forker.py,sha256=C52zONah1E5BNsNzOILohDKl2QBXZcJn3t1fm7AedQs,11538
-haystack_integrations/components/connectors/github/repo_viewer.py,sha256=tECbnxaBxqX3zAZQ2MzCrqvKfY-Ml9MGMhgtLKrsmKw,9199
+haystack_integrations/components/connectors/github/file_editor.py,sha256=OEhcp5vViF0kjbIb4jYNkl3jHj3t1m2dY836y1cESBQ,11802
+haystack_integrations/components/connectors/github/issue_commenter.py,sha256=Uwlm6NNOsgHgcLXxZgZkRcxZXbHUsevTmx93GV6vsfs,5688
+haystack_integrations/components/connectors/github/issue_viewer.py,sha256=w_E2rW8uAO2B-ndIDnvv9yW3g9T5C3D5PxICpMo17Cg,7438
+haystack_integrations/components/connectors/github/pr_creator.py,sha256=o0zu7xDY3yd6nYBHOWl7LU7wZGSZg2O4ZAel1D6BkVc,11498
+haystack_integrations/components/connectors/github/repo_forker.py,sha256=tGhz77kSC1t3C-XteMsXqE55fDCcktmmZkh3X1JPxM0,11592
+haystack_integrations/components/connectors/github/repo_viewer.py,sha256=lEhjet13k1IKNbLyzvRflzLIGdiG_HkEwgmfH70OAhs,9269
 haystack_integrations/prompts/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haystack_integrations/prompts/github/__init__.py,sha256=jjkSZGJ76S0EX-ZTv4qrhpxGrwVpBb_TCyqMJFhl2ec,759
+haystack_integrations/prompts/github/__init__.py,sha256=cs_w-7RycC2C9q35pN0jY-McAHWbTIM-j_O2S-AIM7Q,882
 haystack_integrations/prompts/github/context_prompt.py,sha256=RSzISqtaBHaC7v6rcyyxt2vxmbBVp5OHsWR6Z2wp5pk,8783
 haystack_integrations/prompts/github/file_editor_prompt.py,sha256=_ro-I3MbVIpYpVFJbSpj4TuzbKLX7wTGn55Q95q8jFE,3301
 haystack_integrations/prompts/github/issue_commenter_prompt.py,sha256=EPynR1z6joRMowsse5hHjkDmpQljYeEBK4fCCxeBCvY,904
 haystack_integrations/prompts/github/issue_viewer_prompt.py,sha256=QlEjfrnoTRiZYlbySMbGu2EP2jfi62c3qfEPNuV_bUc,930
 haystack_integrations/prompts/github/pr_creator_prompt.py,sha256=tNC9BdzIowZ42o8bmnrJ46aonIzMfVHRrZopwryiABI,3944
+haystack_integrations/prompts/github/repo_forker_prompt.py,sha256=VU-80JpGFP5R7haEHQEiKYAnHzU1iSKCD4qUThCpudA,2654
 haystack_integrations/prompts/github/repo_viewer_prompt.py,sha256=JkU2ODn06Vs_YQozF1H0vYym7jzczSdN1kAOXSD5IkA,3257
 haystack_integrations/prompts/github/system_prompt.py,sha256=xiOEAbENJiLHL8M1qrgSdUxrfguAphI_6B0kqelxDok,4209
 haystack_integrations/tools/py.typed,sha256=47DEQpj8HBSa-_TImW-5JCeuQeRkm5NMpJWZG3hSuFU,0
-haystack_integrations/tools/github/__init__.py,sha256=FyNJ5F0IO2Xied-wP6utoMB13lPLK1Y0fAu7YlKhWu0,532
+haystack_integrations/tools/github/__init__.py,sha256=ZJKLyVZRXcg5mU-AdH_Xk1rNLeiItlPqgmY6eTqFSTA,611
 haystack_integrations/tools/github/file_editor_tool.py,sha256=ETvDnSqjaXgzHyo8nNtqhxgZf0RiM4Z7k82TDyOLPTo,5178
 haystack_integrations/tools/github/issue_commenter_tool.py,sha256=AVlto9NxLLJcnmW-U2PZhOoeagICh7STQR5_paXfY2Y,5125
 haystack_integrations/tools/github/issue_viewer_tool.py,sha256=mEiDxyx9xuttOR3LEq29eETt4UYF8zBd8uAtWE3TuiI,5065
 haystack_integrations/tools/github/pr_creator_tool.py,sha256=Bfqn1gSsnfkzJg69Dk4DuICnjkviHYIw7vTX9zsaQa4,4824
+haystack_integrations/tools/github/repo_forker_tool.py,sha256=gd50C3Scfl-KZyJySWMrBq_d-HeAU38rMIQZCBHHI84,4834
 haystack_integrations/tools/github/repo_viewer_tool.py,sha256=QWnbpQS3XrmxJ3qbBIjTUR9eOXfHR_MfQgd1ClDS5qE,5883
 haystack_integrations/tools/github/utils.py,sha256=iSIEFulC3KqZvAY1QcrE2rTZJSkCp49SSqC62BTpcs8,3312
-github_haystack-1.1.0.dist-info/METADATA,sha256=Ks5JPUEfFqMCy7N0JCE3leQnQ7VAUqfaGefteHSx94k,1709
-github_haystack-1.1.0.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
-github_haystack-1.1.0.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
-github_haystack-1.1.0.dist-info/RECORD,,
+github_haystack-1.2.1.dist-info/METADATA,sha256=RMkJ0sLH47n1QLRdgXdjkqpUM-DpHga_1Azncpr66RQ,1771
+github_haystack-1.2.1.dist-info/WHEEL,sha256=qtCwoSJWgHk21S1Kb4ihdzI2rlJ1ZKaIurTj_ngOhyQ,87
+github_haystack-1.2.1.dist-info/licenses/LICENSE.txt,sha256=B05uMshqTA74s-0ltyHKI6yoPfJ3zYgQbvcXfDVGFf8,10280
+github_haystack-1.2.1.dist-info/RECORD,,

haystack_integrations/components/connectors/github/file_editor.py

@@ -115,7 +115,9 @@ class GitHubFileEditor:
         """
         headers = self.base_headers.copy()
         if self.github_token is not None:
-            headers["Authorization"] = f"Bearer {self.github_token.resolve_value()}"
+            token_value = self.github_token.resolve_value()
+            if token_value:
+                headers["Authorization"] = f"Bearer {token_value}"
         return headers
 
     def _get_file_content(self, owner: str, repo: str, path: str, branch: str) -> tuple[str, str]:
@@ -225,7 +227,7 @@ class GitHubFileEditor:
     def _delete_file(self, owner: str, repo: str, payload: Dict[str, str], branch: str) -> str:
         """Handle file deletion."""
         try:
-            content, sha = self._get_file_content(owner, repo, payload["path"], branch)
+            _, sha = self._get_file_content(owner, repo, payload["path"], branch)
             url = f"https://api.github.com/repos/{owner}/{repo}/contents/{payload['path']}"
 
             data = {"message": payload["message"], "sha": sha, "branch": branch}

haystack_integrations/components/connectors/github/issue_commenter.py

@@ -67,7 +67,9 @@ class GitHubIssueCommenter:
         """
         headers = self.base_headers.copy()
         if self.github_token is not None:
-            headers["Authorization"] = f"Bearer {self.github_token.resolve_value()}"
+            token_value = self.github_token.resolve_value()
+            if token_value:
+                headers["Authorization"] = f"Bearer {token_value}"
         return headers
 
     def _parse_github_url(self, url: str) -> tuple[str, str, int]:

haystack_integrations/components/connectors/github/issue_viewer.py

@@ -66,7 +66,9 @@ class GitHubIssueViewer:
         """
         headers = self.base_headers.copy()
         if self.github_token:
-            headers["Authorization"] = f"Bearer {self.github_token.resolve_value()}"
+            token_value = self.github_token.resolve_value()
+            if token_value:
+                headers["Authorization"] = f"Bearer {token_value}"
         return headers
 
     def _parse_github_url(self, url: str) -> tuple[str, str, int]:

haystack_integrations/components/connectors/github/pr_creator.py

@@ -65,7 +65,9 @@ class GitHubPRCreator:
         """
         headers = self.base_headers.copy()
         if self.github_token is not None:
-            headers["Authorization"] = f"Bearer {self.github_token.resolve_value()}"
+            token_value = self.github_token.resolve_value()
+            if token_value:
+                headers["Authorization"] = f"Bearer {token_value}"
         return headers
 
     def _parse_issue_url(self, issue_url: str) -> tuple[str, str, str]:

haystack_integrations/components/connectors/github/repo_forker.py

@@ -60,9 +60,9 @@ class GitHubRepoForker:
         :param auto_sync: If True, syncs fork with original repository if it already exists
         :param create_branch: If True, creates a fix branch based on the issue number
         """
-        error_message = "github_token must be a Secret"
         if not isinstance(github_token, Secret):
-            raise TypeError(error_message)
+            msg = "github_token must be a Secret"
+            raise TypeError(msg)
 
         self.github_token = github_token
         self.raise_on_failure = raise_on_failure
@@ -85,7 +85,9 @@ class GitHubRepoForker:
         """
         headers = self.base_headers.copy()
         if self.github_token is not None:
-            headers["Authorization"] = f"Bearer {self.github_token.resolve_value()}"
+            token_value = self.github_token.resolve_value()
+            if token_value:
+                headers["Authorization"] = f"Bearer {token_value}"
         return headers
 
     def _parse_github_url(self, url: str) -> tuple[str, str, str]:

haystack_integrations/components/connectors/github/repo_viewer.py

@@ -109,7 +109,9 @@ class GitHubRepoViewer:
         """
         headers = self.base_headers.copy()
         if self.github_token is not None:
-            headers["Authorization"] = f"Bearer {self.github_token.resolve_value()}"
+            token_value = self.github_token.resolve_value()
+            if token_value:
+                headers["Authorization"] = f"Bearer {token_value}"
         return headers
 
     def to_dict(self) -> Dict[str, Any]:

haystack_integrations/prompts/github/__init__.py

@@ -5,6 +5,7 @@ from .context_prompt import CONTEXT_PROMPT
 from .file_editor_prompt import FILE_EDITOR_PROMPT, FILE_EDITOR_SCHEMA
 from .issue_commenter_prompt import ISSUE_COMMENTER_PROMPT, ISSUE_COMMENTER_SCHEMA
 from .pr_creator_prompt import PR_CREATOR_PROMPT, PR_CREATOR_SCHEMA
+from .repo_forker_prompt import REPO_FORKER_PROMPT, REPO_FORKER_SCHEMA
 from .repo_viewer_prompt import REPO_VIEWER_PROMPT, REPO_VIEWER_SCHEMA
 from .system_prompt import SYSTEM_PROMPT
 
@@ -16,6 +17,8 @@ __all__ = [
     "ISSUE_COMMENTER_SCHEMA",
     "PR_CREATOR_PROMPT",
     "PR_CREATOR_SCHEMA",
+    "REPO_FORKER_PROMPT",
+    "REPO_FORKER_SCHEMA",
     "REPO_VIEWER_PROMPT",
     "REPO_VIEWER_SCHEMA",
     "SYSTEM_PROMPT",

haystack_integrations/prompts/github/repo_forker_prompt.py

@@ -0,0 +1,61 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+REPO_FORKER_PROMPT = """Haystack-Agent uses this tool to fork GitHub repositories in order to contribute to issues.
+Haystack-Agent initiates a fork so it can freely make changes for contributions.
+A fork is required to open a pull request to the upstream repository.
+Haystack-Agent works by forking the repository associated with a given issue.
+
+<usage>
+Pass a `url` string for the GitHub issue you want to work on in a fork.
+It is REQUIRED to pass `url` to use this tool.
+The structure must be "https://github.com/<repo-owner>/<repo-name>/issues/<issue-number>".
+
+Examples:
+
+- {"url": "https://github.com/deepset-ai/haystack/issues/9343"}
+    - will fork the "deepset-ai/haystack" repository to work on issue 9343
+- {"url": "https://github.com/deepset-ai/haystack-core-integrations/issues/1685"}
+    - will fork the "deepset-ai/haystack-core-integrations" repository to work on issue 1685
+</usage>
+
+Haystack-Agent uses the `repo_forker` tool to create a copy (fork) of the target repository into its own account.
+Haystack-Agent ensures the issue URL is valid and points to a real GitHub issue.
+It parses the URL to identify the correct repository.
+
+<thinking>
+- Does this issue belong to the repository I need to work on?
+- Can I extract the owner and repository name from the URL?
+- Why am I forking this repository? (e.g., to implement a fix, to add a feature)
+- Is there anything special about the branch or base state I should be aware of?
+</thinking>
+
+Haystack-Agent reflects on the results after forking:
+<thinking>
+- Did the fork succeed? Is the fork visible in my account?
+- Can I access, clone, and push to my fork?
+- Are there any permissions or fork-specific settings to configure before proceeding?
+- Which branch will I be working on in the fork?
+</thinking>
+
+IMPORTANT
+Haystack-Agent ONLY forks the repository mentioned in the given issue URL.
+Haystack-Agent does NOT attempt to fork organizations, user profiles, or non-issue URLs.
+Haystack-Agent knows that forking is a prerequisite to contributing changes and creating pull requests.
+
+Haystack-Agent takes notes after the fork:
+<scratchpad>
+- Record the URL of the forked repository
+- Note the original issue being worked on
+- Document any post-fork steps (e.g., git cloning, installing dependencies)
+- Make note of any errors or special setup requirements
+</scratchpad>
+"""
+
+REPO_FORKER_SCHEMA = {
+    "properties": {
+        "url": {"type": "string", "description": "URL of the GitHub issue to work on in the fork."},
+    },
+    "required": ["url"],
+    "type": "object",
+}

haystack_integrations/tools/github/__init__.py

@@ -5,6 +5,7 @@ from .file_editor_tool import GitHubFileEditorTool
 from .issue_commenter_tool import GitHubIssueCommenterTool
 from .issue_viewer_tool import GitHubIssueViewerTool
 from .pr_creator_tool import GitHubPRCreatorTool
+from .repo_forker_tool import GitHubRepoForkerTool
 from .repo_viewer_tool import GitHubRepoViewerTool
 
 __all__ = [
@@ -12,5 +13,6 @@ __all__ = [
     "GitHubIssueCommenterTool",
     "GitHubIssueViewerTool",
     "GitHubPRCreatorTool",
+    "GitHubRepoForkerTool",
     "GitHubRepoViewerTool",
 ]

haystack_integrations/tools/github/repo_forker_tool.py

@@ -0,0 +1,116 @@
+# SPDX-FileCopyrightText: 2023-present deepset GmbH <info@deepset.ai>
+#
+# SPDX-License-Identifier: Apache-2.0
+from typing import Any, Callable, Dict, Optional, Union
+
+from haystack.core.serialization import generate_qualified_class_name
+from haystack.tools import ComponentTool
+from haystack.utils import Secret, deserialize_secrets_inplace
+
+from haystack_integrations.components.connectors.github.repo_forker import GitHubRepoForker
+from haystack_integrations.prompts.github.repo_forker_prompt import REPO_FORKER_PROMPT, REPO_FORKER_SCHEMA
+from haystack_integrations.tools.github.utils import deserialize_handlers, serialize_handlers
+
+
+class GitHubRepoForkerTool(ComponentTool):
+    """
+    A tool for forking Github repository.
+    """
+
+    def __init__(
+        self,
+        *,
+        name: Optional[str] = "repo_forker",
+        description: Optional[str] = REPO_FORKER_PROMPT,
+        parameters: Optional[Dict[str, Any]] = REPO_FORKER_SCHEMA,
+        github_token: Secret = Secret.from_env_var("GITHUB_TOKEN"),
+        raise_on_failure: bool = True,
+        outputs_to_string: Optional[Dict[str, Union[str, Callable[[Any], str]]]] = None,
+        inputs_from_state: Optional[Dict[str, str]] = None,
+        outputs_to_state: Optional[Dict[str, Dict[str, Union[str, Callable]]]] = None,
+    ):
+        """
+        Initialize the GitHub Repo Forker tool.
+
+        :param name: Optional name for the tool.
+        :param description: Optional description.
+        :param parameters: Optional JSON schema defining the parameters expected by the Tool.
+        :param github_token: GitHub personal access token for API authentication
+        :param raise_on_failure: If True, raises exceptions on API errors
+        :param outputs_to_string:
+            Optional dictionary defining how a tool outputs should be converted into a string.
+            If the source is provided only the specified output key is sent to the handler.
+            If the source is omitted the whole tool result is sent to the handler.
+            Example: {
+                "source": "docs", "handler": format_documents
+            }
+        :param inputs_from_state:
+            Optional dictionary mapping state keys to tool parameter names.
+            Example: {"repository": "repo"} maps state's "repository" to tool's "repo" parameter.
+        :param outputs_to_state:
+            Optional dictionary defining how tool outputs map to keys within state as well as optional handlers.
+            If the source is provided only the specified output key is sent to the handler.
+            Example: {
+                "documents": {"source": "docs", "handler": custom_handler}
+            }
+            If the source is omitted the whole tool result is sent to the handler.
+            Example: {
+                "documents": {"handler": custom_handler}
+            }
+        """
+        self.github_token = github_token
+        self.raise_on_failure = raise_on_failure
+        self.outputs_to_string = outputs_to_string
+        self.inputs_from_state = inputs_from_state
+        self.outputs_to_state = outputs_to_state
+
+        repo_forker = GitHubRepoForker(
+            github_token=github_token,
+            raise_on_failure=raise_on_failure,
+        )
+
+        super().__init__(
+            component=repo_forker,
+            name=name,
+            description=description,
+            parameters=parameters,
+            outputs_to_string=self.outputs_to_string,
+            inputs_from_state=self.inputs_from_state,
+            outputs_to_state=self.outputs_to_state,
+        )
+
+    def to_dict(self) -> Dict[str, Any]:
+        """
+        Serializes the tool to a dictionary.
+
+        Returns:
+            Dictionary with serialized data.
+        """
+        serialized = {
+            "name": self.name,
+            "description": self.description,
+            "parameters": self.parameters,
+            "github_token": self.github_token.to_dict() if self.github_token else None,
+            "raise_on_failure": self.raise_on_failure,
+            "outputs_to_string": self.outputs_to_string,
+            "inputs_from_state": self.inputs_from_state,
+            "outputs_to_state": self.outputs_to_state,
+        }
+
+        serialize_handlers(serialized, self.outputs_to_state, self.outputs_to_string)
+        return {"type": generate_qualified_class_name(type(self)), "data": serialized}
+
+    @classmethod
+    def from_dict(cls, data: Dict[str, Any]) -> "GitHubRepoForkerTool":
+        """
+        Deserializes the tool from a dictionary.
+
+        :param data:
+            Dictionary to deserialize from.
+        :returns:
+            Deserialized tool.
+        """
+        inner_data = data["data"]
+        deserialize_secrets_inplace(inner_data, keys=["github_token"])
+        deserialize_handlers(inner_data)
+        return cls(**inner_data)