Skip to content

docs: guide LLM-specific tweaks through model features #3375

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
enyst wants to merge 1 commit into
base: main
Choose a base branch
from
+1 −0
Draft

docs: guide LLM-specific tweaks through model features #3375

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions AGENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -113,6 +113,7 @@ When reviewing code, provide constructive feedback:
- Do not expose settings schema versions as public `CURRENT_PERSISTED_VERSION` class constants on `AgentSettings` or `ConversationSettings`; keep versioning internal to the `schema_version` field/defaults and private module constants.
- `ConversationSettings` owns the conversation-scoped confirmation controls directly (`confirmation_mode`, `security_analyzer`); keep those fields top-level on the model and grouped into the exported `verification` section via schema metadata rather than nested helper models, and prefer the direct settings-model constructor `create_request(...)` over separate request-wrapper helpers.
- Anthropic malformed tool-use/tool-result history errors (for example, missing or duplicated ``tool_result`` blocks) are intentionally mapped to a dedicated `LLMMalformedConversationHistoryError` and caught separately in `Agent.step()`, so recovery can still use condensation while logs preserve that this was malformed history rather than a true context-window overflow.
- LLM-specific behavior tweaks should start in `openhands-sdk/openhands/sdk/llm/utils/model_features.py` whenever they can be expressed as model/provider capabilities. Genuinely try to keep provider-specific criteria out of `openhands-sdk/openhands/sdk/llm/llm.py`; only touch `llm.py` when the behavior cannot be represented cleanly in the feature registry or a focused helper.
- AgentSkills progressive disclosure goes through `AgentContext.get_system_message_suffix()` into `<available_skills>`, and `openhands.sdk.context.skills.to_prompt()` truncates each prompt description to 1024 characters because the AgentSkills specification caps `description` at 1-1024 characters.
- Workspace-wide uv resolver guardrails belong in the repository root `[tool.uv]` table. When `exclude-newer` is configured there, `uv lock` persists it into the root `uv.lock` `[options]` section as both an absolute cutoff and `exclude-newer-span`, and `uv sync --frozen` continues to use that locked workspace state.
- `pr-review-by-openhands` delegates to `OpenHands/extensions/plugins/pr-review@main`. Repo-specific reviewer instructions live in `.agents/skills/custom-codereview-guide.md`, and because task-trigger matching is substring-based, that `/codereview` skill is also auto-injected for the workflow's `/codereview-roasted` prompt.
Expand Down
Loading