issues Search Results · language:Edge language:Python linked:pr linked:pr language:Java language:Java language:Python
Filter by
179k results
Follow-up from PR #17: https://github.com/jgravelle/jdocmunch-mcp/pull/17
The gap
Downstream MCP workflows need a stable way to cite the exact documentation snapshot used for retrieval.
Today, an indexed ...
Problem Statement
The openextract CLI only supports a single positional input_file and always calls sync extract() without token usage. It
does not expose batch extraction, --media-type, reading from ...
enhancement
Problem Statement
The README API reference section only documents extract(), but the package exports several other public entry points
(extract_async, extract_many, extract_many_async, extract_with_usage, ...
documentation
enhancement
Problem Statement
examples/ only demonstrates single-file extract() (invoice, receipt, meeting notes). There are no runnable samples for
extract_many or extract_with_usage, which are key APIs since v0.5 ...
documentation
enhancement
Problem Statement
URL fetching uses hardcoded constants (_URL_FETCH_TIMEOUT = 30.0, _MAX_REDIRECTS = 10). Large files or slow hosts cannot
be tuned without vendoring/forking. This is inconsistent with ...
enhancement
Problem Statement
The package has typed public APIs (TypeVar, BinaryIO, etc.) but does not ship a py.typed marker and has no static type
checking in CI. Editor autocomplete and downstream type checkers ...
enhancement
Problem Statement
max_retries and retry_backoff exist only on sync extract(). extract_async, extract_with_usage, extract_with_usage_async,
and batch helpers (extract_many, extract_many_async) call the ...
enhancement
Problem Statement
Core pyproject.toml dependencies bundle every pydantic-ai-slim provider extra (anthropic, bedrock, cohere, google, groq,
huggingface, mistral, openai, openrouter, xai, logfire). Users ...
enhancement
Context
Sub-issue of #58 (repo-scope tool-config prohibition). Companion to the GitHub MCP server work in #1063.
#1063 adds a local GitHub MCP server by special exception. The server declaration belongs ...
threat:intel-needed
Bug
Every POST /chat request returns HTTP 500 because app/config.py line 22 defaults AZURE_OPENAI_DEPLOYMENT to gpt-4o-prod,
which does not exist on the Azure OpenAI resource. The correct deployment name ...
bug

Learn how you can use GitHub Issues to plan and track your work.
Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub IssuesProTip! Restrict your search to the title by using the in:title qualifier.