Skip to content
Permalink

Comparing changes

Choose two branches to see what’s changed or to start a new pull request. If you need to, you can also or learn more about diff comparisons.

Open a pull request

Create a new pull request by comparing changes across two branches. If you need to, you can also . Learn more about diff comparisons here.
base repository: ginkida/agent-runner
Failed to load repositories. Confirm that selected base ref is valid, then try again.
Loading
base: v1.0.0
Choose a base ref
...
head repository: ginkida/agent-runner
Failed to load repositories. Confirm that selected head ref is valid, then try again.
Loading
compare: v1.0.1
Choose a head ref
  • 1 commit
  • 5 files changed
  • 1 contributor

Commits on Feb 27, 2026

  1. Fix tool result error swallowing and duplicate history in all providers 

    Two bugs fixed:

1. ToolResultData was missing an Error field, so when any tool failed
   the error message was silently dropped from SSE events — clients saw
   {"success":false,"content":""} with no diagnostic info.

2. The agent loop adds function results to history before calling
   SendFunctionResponse, but all three providers (OpenAI, Gemini,
   Anthropic) also appended the results parameter separately, creating
   duplicate tool messages. OpenAI rejected these because the duplicates
   had no matching preceding tool_calls.
    @ginkida
    ginkida committed Feb 27, 2026
    Configuration menu
    Copy the full SHA
    42edbbf View commit details
    Browse the repository at this point in the history
Loading