Skip to content

Start v1.0.0 Jev Fast Mode with Phase 66 timing and benchmarks - #153

Open
LakshmanTurlapati wants to merge 384 commits into
mainfrom
Jev
Open

LakshmanTurlapati wants to merge 384 commits into
mainfrom
Jev

Conversation

@LakshmanTurlapati

Copy link
Copy Markdown
Member

Summary

This starts the v1.0.0 Jev Fast Mode milestone and relabels the former Full App Catalog milestone as v0.13.0, with research, roadmap, and archived planning updated to match. Phase 66 records MCP and autopilot call timing, projects timing, tokens, and cost in journal-backed session detail, and prices grok-4.3 with provider-first labels. It adds a repeatable benchmark suite: task schema, loopback fixtures, a frozen core corpus, Claude Code and Cursor host-stream parsers, and a seeded ABBA runner with MCP, CDP, Claude Code, and Cursor drivers plus a baseline report. The history-export plan is closed because the source sessions were lost in an extension reinstall. Content clicks now activate their target once.

Test plan

  • Run the Phase 66 benchmark unit suites in the root test chain
  • Confirm journal-backed MCP session detail shows timing, tokens, and cost
  • Confirm a content click activates its target only once

Made with Cursor

@chatgpt-codex-connector

chatgpt-codex-connector Bot commented Oct 14, 2026 •

Copy link
Copy Markdown

Codex Review Summary

This comment shows the latest Codex review activity on this pull request.

Review Status Commit Review trigger
📝 Code Review ⚠️ Failed 2026-10-14T20:16:49.290784Z 70a00bb PR opened
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" or "@codex security review".

Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings.

…xpect

- READMEs state 73 registered tools; root table gains Task lifecycle (3) and Settings (1)
- mcp/README.md gains Task Lifecycle, Settings and Same-call checks sections and a contract marker
- tool-count-docs.js checks the documented count against the built tools/list, outcome-aware
- parity test exercises both doc states on synthetic texts; skill tree gains settings and expect
- feature chip, Agent path description, setup step and MCP summary row name no tool count
- a withheld fsb-mcp-server 0.12.0 can no longer force a post-V4 extension edit

This branch has not been deployed

No deployments
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