Conversation
- Standardized all 30 SDK guide files with consistent format:
- Added <Note> components with GitHub example links
- Used auto-sync code blocks with 'icon' and 'expandable' attributes
- Added 'Running the Example' bash code blocks
- Included brief explanations with line highlights
- Added 'Next Steps' sections with related links
- Merged anthropic-thinking.mdx and responses-reasoning.mdx into model-reasoning.mdx:
- Created unified guide covering both Anthropic thinking blocks and OpenAI responses reasoning
- Single example demonstrating both approaches
- Deleted old separate documentation files
- Updated docs.json navigation:
- Organized all SDK guides into logical categories:
* Getting Started (hello-world, custom-tools, mcp)
* Agent Configuration (llm-registry, llm-routing, model-reasoning)
* Conversation Management (persistence, pause-and-resume, confirmation-mode, etc.)
* Agent Capabilities (activate-skill, async, planning-agent-workflow, etc.)
* Agent Behavior (stuc * Agent Behavior (stuc * Agent Behavior (stuc * Ag n * Agent Behavior (stuc * Agent Behavnces in sdk/arch/sdk/llm.mdx
Co-authored-by: openhands <openhands@all-hands.dev>
Synced from agent-sdk ref: main
Synced from agent-sdk ref: main
This reverts commit a651e92.
| ``` | ||
|
|
||
|
|
||
| ## What is a Remote Agent Server? |
There was a problem hiding this comment.
| ## What is a Remote Agent Server? | |
| ## What is an Agent Server? |
I feel this is going to be confusing: "Remote" includes Local, Docker, and API... 🤔
There was a problem hiding this comment.
I'm not sure it's because we use a workspace in all cases 🤔
Idk, in any case, if we rename, there is more to rename below
| Server --> Workspace[Workspace] | ||
|
|
||
| subgraph Workspace Types | ||
| Workspace --> Local[Local Folder] |
There was a problem hiding this comment.
Here we have "Local", and yes, I think we'd be better off to just name this section and usages in it simply "Agent Servers"...
|
Wow, oops! 😂 A screenshot for posterity, before I reset --hard So last night I wanted OH to
But I didn't prompt clearly, on the contrary I said 'docs' for some reason. So it committed here, on the synced copy. The sync bot didn't like it 😂 ...and the rest is history. (I copied this branch with the battle locally for fun: OpenHands-GPT-5 has occasionally ThinkAction blocks, and I see how it happened: it progressively convinced itself that it has to silence the |
…r code blocks\n\n- Use LLM_API_KEY and RUNTIME_API_URL in run instructions\n- Keep runtime.eval.all-hands.dev until openhands runtime domain is live\n- Do not modify synced code blocks; changes will come via agent-sdk PR #872\n\nCo-authored-by: openhands <openhands@all-hands.dev>\n
enyst
left a comment
enyst
left a comment
There was a problem hiding this comment.
I love a lot, a lot, the persistent descriptions of seamless passage from local to remote! I actually read it all, in detail, all added docs. 😅
Made only some tiny tweaks. I do think we will need to adjust somehow the "Remote Agent Server" and some related occurrences, to probably "Agent Server". But I'm leaving it alone for now, maybe there's something to think about there, or maybe we can adjust it at the next confusion.
3 participants
Summary of changes