Merged
Conversation
Restructure docs to mirror the README's narrative flow: - Add new core/ section with agent-loop, context-control, sessions, and file-attachments pages covering features previously undocumented - Rewrite landing page with README tagline and 6 feature cards - Rewrite concepts/index.md as tighter overview with linked feature table - Expand CLI, REPL, and MCP pages with piping, chaining, resume, sidecar, and Cursor integration content from README - Update recipes with pre-built agent configs (coding-agent, code-review-agent) and --exec scripting - Expand configuration reference with compaction and toolTimeout fields - Update quick-start with pattern resolution example and new next-steps - Remove redundant concepts/config.md and concepts/providers.md (content consolidated in configuration/ and providers/) - Reorganize sidebar: Getting Started → Core → Interfaces → Features → Providers → Reference https://claude.ai/code/session_012xmYtDCEZhMcnHEw5N1bqk
- Thread ra's core philosophy throughout README and docs: "get out of the model's way" — tools are self-describing, the model decides what to do, no prompt engineering gymnastics or rigid workflow graphs - Add "See also" cross-links to every page for proper navigation - Expand thin pages: sessions (list command, storage format), file attachments (format table, provider support matrix), HTTP mode (full SSE event types, sessionId, ask_user), API reference (complete SSE types table, request/response schemas, resume example) - Complete configuration reference: split fields into categorized tables (Core, Skills, Compaction, Context, Storage, HTTP, Interface), add links to provider setup pages - Polish all 6 provider pages: add cross-links, custom base URL docs for Anthropic, prompt caching section, Bedrock model ID example - Add VitePress footer, edit link, Providers nav item - Expand install page with provider setup step and next-steps links - Polish landing page tagline to match philosophy - Add MCP link to modelcontextprotocol.io, MCP client tool discovery explanation, sidecar description https://claude.ai/code/session_012xmYtDCEZhMcnHEw5N1bqk
The framework stays out of the way by default, but users can build whatever workflows they want via system prompts, middleware, and skills. Remove prescriptive language like "no workflow graphs" and "no prompt engineering gymnastics" — those are user choices, not framework constraints. https://claude.ai/code/session_012xmYtDCEZhMcnHEw5N1bqk
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
2 participants
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.
No description provided.