Labels

• area:agent

  Single agent invocation: identity, configuration, reasoning/planning loop
• area:agent-orchestration

  Composition above single agent: workflow execution, handoffs, delegation across agents
• area:embeddings

  Embedding requests and their results
• area:evaluation

  Evaluation of GenAI runs: evaluator identity, runs, scores, verdicts
• area:inference

  Single LLM call: model identity, request parameters, response and finish info, choices
• area:mcp

  Conventions in mcp.* namespace: MCP transport, tool listing/approval, MCP-specific semantics
• area:memory

  Agent memory: store operations, record lifecycle, search, memory-layer taxonomy
• area:messages

  Shape/content of input and output messages, parts, instructions, modalities, citations
• area:retrieval

  Retrieval and vector databases: operations and returned documents/scores
• area:streaming

  Telemetry only for streamed responses: TTFT, TPOT, inter-token-latency, partial events
• area:token-counts

  Token usage: input/output counts, breakdowns (cached, reasoning), per-modality, totals
• area:tools

  Tool definitions and tool calls: declaration, execution, tool-call/result content shape
• bug

  Something isn't working
• dashboard

  Pull request review dashboard
• dependencies
• documentation

  Improvements or additions to documentation
• duplicate

  This issue or pull request already exists
• enhancement

  New feature or request
• good first issue

  Good for newcomers
• help wanted

  Extra attention is needed
• invalid

  This doesn't seem right
• needs author feedback

  Issue/PR is waiting on a response from the author
• python:uv

  Pull requests that update python:uv code
• question

  Further information is requested
• stale

  Issue/PR has been inactive and will be closed soon
• wontfix

  This will not be worked on