feat: auto-reload, multi-framework detection, conversational mock fix#97
Merged
cristipufu merged 2 commits intomainfrom Mar 2, 2026
Merged
feat: auto-reload, multi-framework detection, conversational mock fix#97cristipufu merged 2 commits intomainfrom
cristipufu merged 2 commits intomainfrom
Conversation
- Auto-reload runtime factory when Python files change instead of showing a manual reload popup. Falls back to the popup when runs are in progress or reload fails. - Clear stale reload toast when a subsequent auto-reload succeeds. - Add detection for llama_index.json, agent_framework.json, google_adk.json, pydantic_ai.json, openai_agents.json in agent project context. - Broaden UiPath conversational input detection to match schemas with contentParts/data/inline structure (without requiring userSettings or $defs). Mock output only includes userSettings when the schema declares it. - Make ReloadToast more compact with aria-label on dismiss button. - Bump version to 0.0.70. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
cristipufu
force-pushed
the
feat/auto-reload-multi-framework
branch
from
e769402 to
3f7e407
Compare
- Add OTEL-style trace inspector panel showing per-LLM-call spans with input messages, output, tool calls, token usage, and timing - Add git-style diff view for edit_file tool calls in both trace panel and chat approval/detail cards (shared DiffView component) - Add Trace button in agent chat sidebar header to open inspector tab - Fix system prompt to be framework-agnostic: agents can live in any config file (pydantic_ai.json, langgraph.json, etc.), not just uipath.json — prevents agent from writing to wrong config - Deduplicate "Available reference files" list in skill summaries (was repeated 6x, now appended once) - Trim bloated skill section TOCs from system prompt to save tokens - Clarify bash tool runs via cmd.exe on Windows - Bump bash timeout from 30s to 120s for long-running eval commands - Fix eval command in Full Build Cycle to show <name> <eval-file> syntax - Fix Windows case-sensitivity bug in glob/grep path resolution - Bump version to 0.0.71 Co-Authored-By: Claude Opus 4.6 <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
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
llama_index.json,agent_framework.json,google_adk.json,pydantic_ai.json,openai_agents.jsonin addition touipath.jsonandlanggraph.json.contentParts/data/inlinemessage shape directly, without requiringuserSettingsor$defs. Mock output only includesuserSettingswhen the schema declares it.Test plan
.pyfile while no runs are active — factory should auto-reload, entrypoints refresh silently (no toast).pyfile while a run is active — toast should appear prompting manual reloadcontentParts/data/inline(nouserSettings/$defs)userSettings+$defs)🤖 Generated with Claude Code