Repository navigation
feat(mcp)!: get_container returns the full event timeline; remove get_container_transport_events - #515
Merged
Conversation
get_container reduced transport events to a count and the event with the largest timestamp. Future estimates outrank actual events, and a far-out estimate on another voyage outranked the current ETA, so agents quoted the wrong arrival date unless they also called get_container_transport_events. Transport events now always load, and events.timeline lists every event oldest first in the same shape as get_container_transport_events (vessel, voyage, location, invalidated_at). latest_event is removed. Passing transport_events in include is accepted and changes nothing. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Contributor
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
|
The latest updates on your projects. Learn more about Vercel for GitHub.
|
Contributor
Shadow risk calibration
Calibration result: agreement. Shadow risk never blocks or enables merge. Keep it in observation mode until roughly 50 pull requests have human-reviewed labels, then calibrate before considering any policy use. |
Carriers report several estimates for the same arrival. Sorted by estimated date, the last one listed is not the current one; without the report time the model picked it. reported_at (the event's created_at) lets the latest report win, and the get_container description says so. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
get_container returns the same timeline in events.timeline, so the second tool only gave agents two ways to read a container and a reason to stop at the first. The timeline formatter moves to lib/event-timeline.ts. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>
alosec
marked this pull request as ready for review
November 13, 2026 21:26
This branch was successfully deployed
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.
Why
get_containerwithtransport_eventssummarized events as a count plus the single event with the largest timestamp. Future estimates always outrank actual events, and when a carrier reports arrival estimates on two voyages, the furthest-out one wins. Agents then quote that date as the ETA without seeing the current estimate.Even with every event visible, carriers report several estimates for the same arrival. Sorted by estimated date, the last one listed is not the current one, and nothing said which was reported most recently.
What
get_container.include: ["transport_events"]is still accepted but changes nothing.events.timelinelists every event oldest first, with vessel, voyage, location andinvalidated_at.reported_at(the event'screated_at). Theget_containerdescription says the current ETA is the estimate with the latestreported_at.events.latest_eventis removed.events.countandevents.rail_events_countstill count active events.values atevents.timeline[n].value.docs/mcp/home.mdxupdated; tools/list and instructions snapshots regenerated.Removes
get_container_transport_eventsget_containerreturns the same timeline, so the second tool is gone (registry, server, feature map, tests, docs, changelog). The timeline formatter moves tolib/event-timeline.ts. Breaking for MCP clients that call it; the replacement isget_container→events.timeline. The default tools/list goes from 31 to 30.The directory listing files (
chatgpt-app-submission.json,claude-connector-submission.json) drop the tool in a separate commit. The submitted listings themselves are unchanged until they are resubmitted.Verification
vp run check,vp run build,npm run agent-verifypass.reported_at.mainlatest_eventwas a stale estimate months outreported_at🤖 Generated with Claude Code