docs(specs): add claude-code agent-runner backend brainstorm#108
Open
andreybavt wants to merge 16 commits into
Open
docs(specs): add claude-code agent-runner backend brainstorm#108andreybavt wants to merge 16 commits into
andreybavt wants to merge 16 commits into
Conversation
Locks the design for a new `'claude-code'` value in `KtxLlmBackend` that routes KTX agentic LLM calls through `@anthropic-ai/claude-agent-sdk`, reusing the user's existing `claude login` session. MVP scope: degraded tool-call repair and no telemetry, both documented as known gaps.
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds the post-brainstorm design doc for a new
claude-codeagent-runner backend that would route KTX agent LLM calls through@anthropic-ai/claude-agent-sdk, reusing the user's existing local Claude Code session. Documents goals, non-goals, architecture, decisions (Q1–Q5 + naming/cwd/tool-adapter), implementation surface, verified evidence, and open items for the follow-up plan. Refined across three adversarial review iterations to scope the change to agent-runner only, lock the runner-port boundary, and nail down SDK isolation (built-in tools, filesystem settings, skills) and stop-reason mapping.Test plan