Skills agent - #80
Merged
Merged
Conversation
… run/init param plumbing
Backend
- list_operators (operation_id="list_operators", route /by_category) now
REQUIRES a `category` argument; missing/invalid arg returns a structured
ValidationBizError with valid_categories + did_you_mean (difflib) + a
three-step recovery hint, instead of returning the full ~145-operator
catalog and overflowing the agent context.
- list_operator_categories now returns {count, use_for, not_for, examples}
per category (new app/services/operator_category_guide.py), distilled
from observed agent failure modes (e.g. text_sft.not_for explicitly
routes QA-generation to core_text). Methods without any construction
skill inherit operator-selection guidance directly from this response.
- Frontend operator palette keeps unrestricted access via a new
list_operators_all (route /, NOT MCP-whitelisted).
- dataflow_engine: drop run/init params the operator's signature can't
accept (e.g. agent-supplied system_prompt on operators that don't take
it) instead of crashing with TypeError; unwrap llm_serving={"id": ...}
dict to its scalar id (was crashing with unhashable-type).
Skills
- Promote .claude/skills/{dataflow-dev,dataflow-operator-builder,
generating-dataflow-pipeline,prompt-template-builder} from the stale
"* copy/" siblings (renames, not duplicates).
- .gitignore now excludes .claude/skills/* copy/ to prevent recurrence.
Evaluation impact (12 tasks x 3 reps x 4 agent configs, see emnlp paper):
- Mean operator errors: 1.87 -> 0.24 across the four agents (7.8x).
- Context-overflow failure rate: 5.7-21.7% -> 0% on all four conditions.
- End-to-end execution success: best agent rises from ~16% to 47.2%.
- Add agent adapter abstraction (base, claude, codex, cursor adapters) - Add factory dispatch for WebUI chat (claude + codex headless) - Cursor is IDE-mode only (connects via MCP, not dispatched by backend) - Codex supports dual auth: API key + OPENAI_BASE_URL OR codex login OAuth - Frontend: agent dropdown (claude/codex), Cursor IDE hint in empty state - scripts/setup_all.sh: one-command full-stack installer (idempotent) - scripts/start.sh: backend start/stop/status helper - scripts/setup_agent.sh: per-agent MCP config writer - AGENT_SETUP.md: agent-facing self-setup guide (from zero to working) - AGENTS.md: Codex instruction file with MCP activation guide - .cursor/rules/dataflow-pipeline.mdc: Cursor rules with setup hints - README.md: simplified Quick Start with 'let agent configure' path - Fix pipeline_registry param parsing for dict format - Fix dataflow_engine VAR_KEYWORD unpacking - Fix prompted_generator None + str crash Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
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.
No description provided.