Open
Conversation
…mproved clarity and flexibility.
… registration and prompt rendering.
… update method signatures for improved clarity and usability.
…hain_tools.py` and update imports across executors.
…lity across executors.
… `RUN_SQL_QUERY_TOOL_DESCRIPTION` for improved clarity
# Conflicts: # databao/agent/api.py # databao/agent/duckdb/react_tools.py # databao/agent/executors/base.py # databao/agent/executors/claude_code/claude_model_wrapper.py # databao/agent/executors/claude_code/executor.py # databao/agent/executors/langchain_tools.py # databao/agent/executors/utils.py
Contributor
Author
|
model does in fact use dce, but subsequent |
Contributor
There was a problem hiding this comment.
Pull request overview
Adds Databao Context Engine (DCE) context-search tooling support to the Claude Code executor path, and refactors shared DuckDB SQL execution + context-search logic to reusable utilities.
Changes:
- Centralize
execute_duckdb_sqlinto a newdatabao.agent.duckdb.utilsmodule and update executors to use it. - Add DCE context search helpers (including query expansion + RRF) into
executors/utils.pyand reuse them from LangChain tools. - Enable and wire a
search_contextMCP tool for Claude Code when the active domain supports DCE context.
Reviewed changes
Copilot reviewed 7 out of 7 changed files in this pull request and generated 5 comments.
Show a summary per file
| File | Description |
|---|---|
| databao/agent/executors/utils.py | Adds DCE context search helpers and query-expansion search implementation. |
| databao/agent/executors/react_duckdb/executor.py | Updates DuckDB SQL execution import to the new shared helper. |
| databao/agent/executors/langchain_tools.py | Refactors DCE search tools to reuse shared search helpers; introduces tool description constants. |
| databao/agent/executors/claude_code/executor.py | Enables DCE search for Claude Code when domain supports context; passes domain into wrapper. |
| databao/agent/executors/claude_code/claude_model_wrapper.py | Adds MCP search_context tool when domain is _DCEProjectDomain. |
| databao/agent/duckdb/utils.py | New shared implementation of execute_duckdb_sql. |
| databao/agent/duckdb/react_tools.py | Removes duplicated SQL helper; imports shared helper; avoids potential circular import via local import. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
You can also share your feedback on Copilot code review. Take the survey.
| to get the best results. | ||
|
|
||
| Args: | ||
| query: Natural language query to search the context for relevant results. |
| @@ -0,0 +1,16 @@ | |||
| import pandas as pd | |||
| from _duckdb import DuckDBPyConnection | |||
Comment on lines
+185
to
+209
| if self._domain.supports_context: | ||
| if isinstance(self._domain, _DCEProjectDomain): | ||
|
|
||
| @tool( | ||
| "search_context", | ||
| SEARCH_CONTEXT_TOOL_DESCRIPTION, | ||
| {"retrieve_text": str}, | ||
| annotations=ToolAnnotations(readOnlyHint=True), | ||
| ) | ||
| async def search_context(args: dict[str, Any]) -> dict[str, Any]: | ||
| if retrieve_text := args.get("retrieve_text", ""): | ||
| return { | ||
| "content": [ | ||
| { | ||
| "type": "text", | ||
| "text": json.dumps(_search_context(retrieve_text, domain=self._domain)), # type: ignore[arg-type] | ||
| } | ||
| ] | ||
| } | ||
| return {"content": [{"type": "text", "text": json.dumps({"error": "No retrieve text provided"})}]} | ||
|
|
||
| tools.append(search_context) | ||
| else: | ||
| raise ValueError(f"Search context tool is not supported for domain type: {type(self._domain)}") | ||
|
|
| "content": [ | ||
| { | ||
| "type": "text", | ||
| "text": json.dumps(_search_context(retrieve_text, domain=self._domain)), # type: ignore[arg-type] |
Comment on lines
+77
to
+83
| def search_context(query: str, *, domain: _DCEProjectDomain) -> list[dict[str, Any]]: | ||
| """Search the context for relevant information matching the given query text. | ||
| Args: | ||
| query: Natural language query to search the context for relevant results. | ||
| domain: The domain object to use to search the context. | ||
| """ | ||
| search_result_list = domain.search_context(query, datasource_name=None) |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Uh oh!
There was an error while loading. Please reload this page.