Skip to content

chore: merge dev into main#87

Open
Dan-StrategicAutomation wants to merge 2 commits into
mainfrom
dev
Open

chore: merge dev into main#87
Dan-StrategicAutomation wants to merge 2 commits into
mainfrom
dev

Conversation

@Dan-StrategicAutomation

Copy link
Copy Markdown
Collaborator

Merge dev back into main after stashing, conflict resolution, and dependency alignment.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 950109ee1b

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

"arxiv_search_async": arxiv_search_async,
"deep_research_async": deep_research_async,
"browser_visit_async": browser_visit_async,
"crawl4ai_fetch_async": crawl4ai_fetch_async,

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Hide Crawl4AI until the extra is installed

In a default install without the crawl extra, this registry entry is still returned by list_tools(), so GraphWeaver can plan a web node around crawl4ai_fetch_async even though execution will only return the setup error from crawl4ai_fetch(). Since the docs describe the extra as what enables this tool, gate it with an availability check such as importlib.util.find_spec("crawl4ai") so the planner only sees it after the optional dependency is installed.

Useful? React with 👍 / 👎.

with open(inputs_path, "rb") as f:
inputs = json.load(f)
if inputs.get("goal") == goal:
if inputs.get("goal") == goal and (include_completed or not _session_state_is_complete(path)):

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Stop searching older sessions after a completed run

When the newest matching session is completed, this condition skips it but keeps scanning and can return an older partial session for the same goal. In the common case where a stale interrupted run remains beside a later successful run, Arachne.forward() will auto-resume the older partial outputs instead of starting fresh, reintroducing the stale-output problem this change is meant to avoid.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant